| [2023-02-24 17:11:14,766][2343622] Saving configuration to /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/config.json... | |
| [2023-02-24 17:11:14,767][2343622] Rollout worker 0 uses device cpu | |
| [2023-02-24 17:11:14,767][2343622] Rollout worker 1 uses device cpu | |
| [2023-02-24 17:11:14,767][2343622] Rollout worker 2 uses device cpu | |
| [2023-02-24 17:11:14,767][2343622] Rollout worker 3 uses device cpu | |
| [2023-02-24 17:11:14,767][2343622] Rollout worker 4 uses device cpu | |
| [2023-02-24 17:11:14,767][2343622] Rollout worker 5 uses device cpu | |
| [2023-02-24 17:11:14,768][2343622] Rollout worker 6 uses device cpu | |
| [2023-02-24 17:11:14,768][2343622] Rollout worker 7 uses device cpu | |
| [2023-02-24 17:11:14,797][2343622] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-24 17:11:14,797][2343622] InferenceWorker_p0-w0: min num requests: 2 | |
| [2023-02-24 17:11:14,815][2343622] Starting all processes... | |
| [2023-02-24 17:11:14,815][2343622] Starting process learner_proc0 | |
| [2023-02-24 17:11:15,520][2343622] Starting all processes... | |
| [2023-02-24 17:11:15,523][2343622] Starting process inference_proc0-0 | |
| [2023-02-24 17:11:15,523][2343622] Starting process rollout_proc0 | |
| [2023-02-24 17:11:15,525][2343698] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-24 17:11:15,525][2343698] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 | |
| [2023-02-24 17:11:15,524][2343622] Starting process rollout_proc1 | |
| [2023-02-24 17:11:15,527][2343622] Starting process rollout_proc2 | |
| [2023-02-24 17:11:15,530][2343622] Starting process rollout_proc3 | |
| [2023-02-24 17:11:15,530][2343622] Starting process rollout_proc4 | |
| [2023-02-24 17:11:15,532][2343622] Starting process rollout_proc5 | |
| [2023-02-24 17:11:15,533][2343622] Starting process rollout_proc6 | |
| [2023-02-24 17:11:15,533][2343622] Starting process rollout_proc7 | |
| [2023-02-24 17:11:15,542][2343698] Num visible devices: 1 | |
| [2023-02-24 17:11:15,559][2343698] Starting seed is not provided | |
| [2023-02-24 17:11:15,559][2343698] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-24 17:11:15,559][2343698] Initializing actor-critic model on device cuda:0 | |
| [2023-02-24 17:11:15,559][2343698] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-24 17:11:15,560][2343698] RunningMeanStd input shape: (1,) | |
| [2023-02-24 17:11:15,571][2343698] ConvEncoder: input_channels=3 | |
| [2023-02-24 17:11:15,751][2343698] Conv encoder output size: 512 | |
| [2023-02-24 17:11:15,751][2343698] Policy head output size: 512 | |
| [2023-02-24 17:11:15,766][2343698] Created Actor Critic model with architecture: | |
| [2023-02-24 17:11:15,766][2343698] ActorCriticSharedWeights( | |
| (obs_normalizer): ObservationNormalizer( | |
| (running_mean_std): RunningMeanStdDictInPlace( | |
| (running_mean_std): ModuleDict( | |
| (obs): RunningMeanStdInPlace() | |
| ) | |
| ) | |
| ) | |
| (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) | |
| (encoder): VizdoomEncoder( | |
| (basic_encoder): ConvEncoder( | |
| (enc): RecursiveScriptModule( | |
| original_name=ConvEncoderImpl | |
| (conv_head): RecursiveScriptModule( | |
| original_name=Sequential | |
| (0): RecursiveScriptModule(original_name=Conv2d) | |
| (1): RecursiveScriptModule(original_name=ELU) | |
| (2): RecursiveScriptModule(original_name=Conv2d) | |
| (3): RecursiveScriptModule(original_name=ELU) | |
| (4): RecursiveScriptModule(original_name=Conv2d) | |
| (5): RecursiveScriptModule(original_name=ELU) | |
| ) | |
| (mlp_layers): RecursiveScriptModule( | |
| original_name=Sequential | |
| (0): RecursiveScriptModule(original_name=Linear) | |
| (1): RecursiveScriptModule(original_name=ELU) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (core): ModelCoreRNN( | |
| (core): GRU(512, 512) | |
| ) | |
| (decoder): MlpDecoder( | |
| (mlp): Identity() | |
| ) | |
| (critic_linear): Linear(in_features=512, out_features=1, bias=True) | |
| (action_parameterization): ActionParameterizationDefault( | |
| (distribution_linear): Linear(in_features=512, out_features=5, bias=True) | |
| ) | |
| ) | |
| [2023-02-24 17:11:16,608][2343747] Worker 7 uses CPU cores [14, 15] | |
| [2023-02-24 17:11:16,626][2343746] Worker 4 uses CPU cores [8, 9] | |
| [2023-02-24 17:11:16,638][2343750] Worker 3 uses CPU cores [6, 7] | |
| [2023-02-24 17:11:16,640][2343744] Worker 1 uses CPU cores [2, 3] | |
| [2023-02-24 17:11:16,669][2343745] Worker 2 uses CPU cores [4, 5] | |
| [2023-02-24 17:11:16,708][2343749] Worker 5 uses CPU cores [10, 11] | |
| [2023-02-24 17:11:16,715][2343726] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-24 17:11:16,715][2343726] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 | |
| [2023-02-24 17:11:16,730][2343726] Num visible devices: 1 | |
| [2023-02-24 17:11:16,758][2343748] Worker 6 uses CPU cores [12, 13] | |
| [2023-02-24 17:11:16,825][2343743] Worker 0 uses CPU cores [0, 1] | |
| [2023-02-24 17:11:17,546][2343698] Using optimizer <class 'torch.optim.adam.Adam'> | |
| [2023-02-24 17:11:17,547][2343698] No checkpoints found | |
| [2023-02-24 17:11:17,547][2343698] Did not load from checkpoint, starting from scratch! | |
| [2023-02-24 17:11:17,547][2343698] Initialized policy 0 weights for model version 0 | |
| [2023-02-24 17:11:17,548][2343698] LearnerWorker_p0 finished initialization! | |
| [2023-02-24 17:11:17,548][2343698] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-24 17:11:17,640][2343726] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-24 17:11:17,641][2343726] RunningMeanStd input shape: (1,) | |
| [2023-02-24 17:11:17,648][2343726] ConvEncoder: input_channels=3 | |
| [2023-02-24 17:11:17,708][2343726] Conv encoder output size: 512 | |
| [2023-02-24 17:11:17,708][2343726] Policy head output size: 512 | |
| [2023-02-24 17:11:18,236][2343622] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-02-24 17:11:18,948][2343622] Inference worker 0-0 is ready! | |
| [2023-02-24 17:11:18,948][2343622] All inference workers are ready! Signal rollout workers to start! | |
| [2023-02-24 17:11:18,961][2343745] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:11:18,961][2343746] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:11:18,961][2343743] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:11:18,961][2343749] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:11:18,966][2343748] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:11:18,966][2343744] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:11:18,975][2343747] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:11:18,977][2343750] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:11:19,171][2343744] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:11:19,174][2343746] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:11:19,174][2343743] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:11:19,243][2343745] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:11:19,245][2343748] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:11:19,356][2343746] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:11:19,359][2343744] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:11:19,427][2343748] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:11:19,496][2343749] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:11:19,561][2343743] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:11:19,635][2343748] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:11:19,702][2343744] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:11:19,725][2343750] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:11:19,763][2343749] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:11:19,803][2343746] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:11:19,804][2343743] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:11:19,893][2343748] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:11:19,916][2343750] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:11:19,952][2343744] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:11:20,019][2343746] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:11:20,028][2343749] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:11:20,101][2343747] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:11:20,240][2343749] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:11:20,241][2343745] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:11:20,296][2343750] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:11:20,325][2343743] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:11:20,369][2343747] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:11:20,471][2343745] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:11:20,530][2343750] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:11:20,679][2343747] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:11:20,777][2343745] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:11:20,815][2343698] Signal inference workers to stop experience collection... | |
| [2023-02-24 17:11:20,819][2343726] InferenceWorker_p0-w0: stopping experience collection | |
| [2023-02-24 17:11:20,912][2343747] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:11:21,610][2343698] Signal inference workers to resume experience collection... | |
| [2023-02-24 17:11:21,610][2343726] InferenceWorker_p0-w0: resuming experience collection | |
| [2023-02-24 17:11:23,236][2343622] Fps is (10 sec: 7372.6, 60 sec: 7372.6, 300 sec: 7372.6). Total num frames: 36864. Throughput: 0: 626.0. Samples: 3130. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) | |
| [2023-02-24 17:11:23,242][2343622] Avg episode reward: [(0, '4.086')] | |
| [2023-02-24 17:11:23,269][2343726] Updated weights for policy 0, policy_version 10 (0.0231) | |
| [2023-02-24 17:11:24,717][2343726] Updated weights for policy 0, policy_version 20 (0.0007) | |
| [2023-02-24 17:11:26,117][2343726] Updated weights for policy 0, policy_version 30 (0.0007) | |
| [2023-02-24 17:11:27,512][2343726] Updated weights for policy 0, policy_version 40 (0.0007) | |
| [2023-02-24 17:11:28,236][2343622] Fps is (10 sec: 18431.9, 60 sec: 18431.9, 300 sec: 18431.9). Total num frames: 184320. Throughput: 0: 4463.4. Samples: 44634. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 17:11:28,242][2343622] Avg episode reward: [(0, '4.252')] | |
| [2023-02-24 17:11:28,243][2343698] Saving new best policy, reward=4.252! | |
| [2023-02-24 17:11:28,928][2343726] Updated weights for policy 0, policy_version 50 (0.0007) | |
| [2023-02-24 17:11:30,360][2343726] Updated weights for policy 0, policy_version 60 (0.0006) | |
| [2023-02-24 17:11:31,782][2343726] Updated weights for policy 0, policy_version 70 (0.0007) | |
| [2023-02-24 17:11:33,190][2343726] Updated weights for policy 0, policy_version 80 (0.0007) | |
| [2023-02-24 17:11:33,236][2343622] Fps is (10 sec: 29081.8, 60 sec: 21845.2, 300 sec: 21845.2). Total num frames: 327680. Throughput: 0: 4426.8. Samples: 66402. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:11:33,244][2343622] Avg episode reward: [(0, '4.526')] | |
| [2023-02-24 17:11:33,247][2343698] Saving new best policy, reward=4.526! | |
| [2023-02-24 17:11:34,623][2343726] Updated weights for policy 0, policy_version 90 (0.0007) | |
| [2023-02-24 17:11:34,792][2343622] Heartbeat connected on Batcher_0 | |
| [2023-02-24 17:11:34,794][2343622] Heartbeat connected on LearnerWorker_p0 | |
| [2023-02-24 17:11:34,800][2343622] Heartbeat connected on InferenceWorker_p0-w0 | |
| [2023-02-24 17:11:34,801][2343622] Heartbeat connected on RolloutWorker_w0 | |
| [2023-02-24 17:11:34,802][2343622] Heartbeat connected on RolloutWorker_w1 | |
| [2023-02-24 17:11:34,807][2343622] Heartbeat connected on RolloutWorker_w3 | |
| [2023-02-24 17:11:34,808][2343622] Heartbeat connected on RolloutWorker_w2 | |
| [2023-02-24 17:11:34,809][2343622] Heartbeat connected on RolloutWorker_w4 | |
| [2023-02-24 17:11:34,810][2343622] Heartbeat connected on RolloutWorker_w5 | |
| [2023-02-24 17:11:34,813][2343622] Heartbeat connected on RolloutWorker_w6 | |
| [2023-02-24 17:11:34,816][2343622] Heartbeat connected on RolloutWorker_w7 | |
| [2023-02-24 17:11:36,090][2343726] Updated weights for policy 0, policy_version 100 (0.0007) | |
| [2023-02-24 17:11:37,537][2343726] Updated weights for policy 0, policy_version 110 (0.0007) | |
| [2023-02-24 17:11:38,236][2343622] Fps is (10 sec: 28262.5, 60 sec: 23347.2, 300 sec: 23347.2). Total num frames: 466944. Throughput: 0: 5462.9. Samples: 109258. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-24 17:11:38,246][2343622] Avg episode reward: [(0, '4.374')] | |
| [2023-02-24 17:11:38,984][2343726] Updated weights for policy 0, policy_version 120 (0.0007) | |
| [2023-02-24 17:11:40,452][2343726] Updated weights for policy 0, policy_version 130 (0.0007) | |
| [2023-02-24 17:11:41,886][2343726] Updated weights for policy 0, policy_version 140 (0.0007) | |
| [2023-02-24 17:11:43,236][2343622] Fps is (10 sec: 28262.5, 60 sec: 24412.1, 300 sec: 24412.1). Total num frames: 610304. Throughput: 0: 6064.6. Samples: 151616. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-24 17:11:43,248][2343622] Avg episode reward: [(0, '4.299')] | |
| [2023-02-24 17:11:43,339][2343726] Updated weights for policy 0, policy_version 150 (0.0007) | |
| [2023-02-24 17:11:44,774][2343726] Updated weights for policy 0, policy_version 160 (0.0007) | |
| [2023-02-24 17:11:46,247][2343726] Updated weights for policy 0, policy_version 170 (0.0007) | |
| [2023-02-24 17:11:47,693][2343726] Updated weights for policy 0, policy_version 180 (0.0007) | |
| [2023-02-24 17:11:48,236][2343622] Fps is (10 sec: 28262.2, 60 sec: 24985.5, 300 sec: 24985.5). Total num frames: 749568. Throughput: 0: 5760.8. Samples: 172826. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2023-02-24 17:11:48,236][2343622] Avg episode reward: [(0, '4.570')] | |
| [2023-02-24 17:11:48,259][2343698] Saving new best policy, reward=4.570! | |
| [2023-02-24 17:11:49,140][2343726] Updated weights for policy 0, policy_version 190 (0.0008) | |
| [2023-02-24 17:11:50,563][2343726] Updated weights for policy 0, policy_version 200 (0.0007) | |
| [2023-02-24 17:11:52,015][2343726] Updated weights for policy 0, policy_version 210 (0.0007) | |
| [2023-02-24 17:11:53,236][2343622] Fps is (10 sec: 28262.4, 60 sec: 25512.2, 300 sec: 25512.2). Total num frames: 892928. Throughput: 0: 6152.8. Samples: 215350. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:11:53,238][2343622] Avg episode reward: [(0, '4.848')] | |
| [2023-02-24 17:11:53,242][2343698] Saving new best policy, reward=4.848! | |
| [2023-02-24 17:11:53,484][2343726] Updated weights for policy 0, policy_version 220 (0.0007) | |
| [2023-02-24 17:11:54,907][2343726] Updated weights for policy 0, policy_version 230 (0.0007) | |
| [2023-02-24 17:11:56,319][2343726] Updated weights for policy 0, policy_version 240 (0.0007) | |
| [2023-02-24 17:11:57,782][2343726] Updated weights for policy 0, policy_version 250 (0.0006) | |
| [2023-02-24 17:11:58,236][2343622] Fps is (10 sec: 28672.2, 60 sec: 25907.2, 300 sec: 25907.2). Total num frames: 1036288. Throughput: 0: 6446.3. Samples: 257854. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:11:58,236][2343622] Avg episode reward: [(0, '4.846')] | |
| [2023-02-24 17:11:59,235][2343726] Updated weights for policy 0, policy_version 260 (0.0007) | |
| [2023-02-24 17:12:00,862][2343726] Updated weights for policy 0, policy_version 270 (0.0008) | |
| [2023-02-24 17:12:02,356][2343726] Updated weights for policy 0, policy_version 280 (0.0007) | |
| [2023-02-24 17:12:03,236][2343622] Fps is (10 sec: 27853.0, 60 sec: 26032.4, 300 sec: 26032.4). Total num frames: 1171456. Throughput: 0: 6174.2. Samples: 277840. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:12:03,236][2343622] Avg episode reward: [(0, '4.947')] | |
| [2023-02-24 17:12:03,239][2343698] Saving new best policy, reward=4.947! | |
| [2023-02-24 17:12:03,847][2343726] Updated weights for policy 0, policy_version 290 (0.0008) | |
| [2023-02-24 17:12:05,268][2343726] Updated weights for policy 0, policy_version 300 (0.0007) | |
| [2023-02-24 17:12:06,687][2343726] Updated weights for policy 0, policy_version 310 (0.0006) | |
| [2023-02-24 17:12:08,150][2343726] Updated weights for policy 0, policy_version 320 (0.0007) | |
| [2023-02-24 17:12:08,236][2343622] Fps is (10 sec: 27443.2, 60 sec: 26214.4, 300 sec: 26214.4). Total num frames: 1310720. Throughput: 0: 7043.1. Samples: 320070. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-24 17:12:08,236][2343622] Avg episode reward: [(0, '6.912')] | |
| [2023-02-24 17:12:08,236][2343698] Saving new best policy, reward=6.912! | |
| [2023-02-24 17:12:09,606][2343726] Updated weights for policy 0, policy_version 330 (0.0008) | |
| [2023-02-24 17:12:11,175][2343726] Updated weights for policy 0, policy_version 340 (0.0007) | |
| [2023-02-24 17:12:12,639][2343726] Updated weights for policy 0, policy_version 350 (0.0007) | |
| [2023-02-24 17:12:13,236][2343622] Fps is (10 sec: 27443.0, 60 sec: 26288.8, 300 sec: 26288.8). Total num frames: 1445888. Throughput: 0: 7036.6. Samples: 361282. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2023-02-24 17:12:13,236][2343622] Avg episode reward: [(0, '8.564')] | |
| [2023-02-24 17:12:13,242][2343698] Saving new best policy, reward=8.564! | |
| [2023-02-24 17:12:14,109][2343726] Updated weights for policy 0, policy_version 360 (0.0007) | |
| [2023-02-24 17:12:15,599][2343726] Updated weights for policy 0, policy_version 370 (0.0007) | |
| [2023-02-24 17:12:17,098][2343726] Updated weights for policy 0, policy_version 380 (0.0007) | |
| [2023-02-24 17:12:18,236][2343622] Fps is (10 sec: 27443.2, 60 sec: 26419.2, 300 sec: 26419.2). Total num frames: 1585152. Throughput: 0: 7014.2. Samples: 382040. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2023-02-24 17:12:18,236][2343622] Avg episode reward: [(0, '8.241')] | |
| [2023-02-24 17:12:18,592][2343726] Updated weights for policy 0, policy_version 390 (0.0008) | |
| [2023-02-24 17:12:20,082][2343726] Updated weights for policy 0, policy_version 400 (0.0007) | |
| [2023-02-24 17:12:21,524][2343726] Updated weights for policy 0, policy_version 410 (0.0007) | |
| [2023-02-24 17:12:22,983][2343726] Updated weights for policy 0, policy_version 420 (0.0007) | |
| [2023-02-24 17:12:23,236][2343622] Fps is (10 sec: 27852.9, 60 sec: 28125.9, 300 sec: 26529.5). Total num frames: 1724416. Throughput: 0: 6984.0. Samples: 423538. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:12:23,236][2343622] Avg episode reward: [(0, '10.228')] | |
| [2023-02-24 17:12:23,263][2343698] Saving new best policy, reward=10.228! | |
| [2023-02-24 17:12:24,436][2343726] Updated weights for policy 0, policy_version 430 (0.0007) | |
| [2023-02-24 17:12:25,914][2343726] Updated weights for policy 0, policy_version 440 (0.0007) | |
| [2023-02-24 17:12:27,379][2343726] Updated weights for policy 0, policy_version 450 (0.0007) | |
| [2023-02-24 17:12:28,236][2343622] Fps is (10 sec: 27852.7, 60 sec: 27989.3, 300 sec: 26624.0). Total num frames: 1863680. Throughput: 0: 6975.6. Samples: 465520. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:12:28,236][2343622] Avg episode reward: [(0, '12.021')] | |
| [2023-02-24 17:12:28,264][2343698] Saving new best policy, reward=12.021! | |
| [2023-02-24 17:12:28,842][2343726] Updated weights for policy 0, policy_version 460 (0.0007) | |
| [2023-02-24 17:12:30,319][2343726] Updated weights for policy 0, policy_version 470 (0.0007) | |
| [2023-02-24 17:12:31,757][2343726] Updated weights for policy 0, policy_version 480 (0.0007) | |
| [2023-02-24 17:12:33,211][2343726] Updated weights for policy 0, policy_version 490 (0.0007) | |
| [2023-02-24 17:12:33,236][2343622] Fps is (10 sec: 28262.3, 60 sec: 27989.3, 300 sec: 26760.5). Total num frames: 2007040. Throughput: 0: 6972.7. Samples: 486596. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-24 17:12:33,236][2343622] Avg episode reward: [(0, '14.858')] | |
| [2023-02-24 17:12:33,239][2343698] Saving new best policy, reward=14.858! | |
| [2023-02-24 17:12:34,673][2343726] Updated weights for policy 0, policy_version 500 (0.0007) | |
| [2023-02-24 17:12:36,167][2343726] Updated weights for policy 0, policy_version 510 (0.0007) | |
| [2023-02-24 17:12:37,680][2343726] Updated weights for policy 0, policy_version 520 (0.0007) | |
| [2023-02-24 17:12:38,236][2343622] Fps is (10 sec: 27852.8, 60 sec: 27921.0, 300 sec: 26777.6). Total num frames: 2142208. Throughput: 0: 6958.1. Samples: 528464. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2023-02-24 17:12:38,236][2343622] Avg episode reward: [(0, '13.124')] | |
| [2023-02-24 17:12:39,147][2343726] Updated weights for policy 0, policy_version 530 (0.0007) | |
| [2023-02-24 17:12:40,649][2343726] Updated weights for policy 0, policy_version 540 (0.0008) | |
| [2023-02-24 17:12:42,118][2343726] Updated weights for policy 0, policy_version 550 (0.0007) | |
| [2023-02-24 17:12:43,236][2343622] Fps is (10 sec: 27443.2, 60 sec: 27852.8, 300 sec: 26840.8). Total num frames: 2281472. Throughput: 0: 6928.3. Samples: 569626. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-24 17:12:43,236][2343622] Avg episode reward: [(0, '14.789')] | |
| [2023-02-24 17:12:43,605][2343726] Updated weights for policy 0, policy_version 560 (0.0007) | |
| [2023-02-24 17:12:45,110][2343726] Updated weights for policy 0, policy_version 570 (0.0006) | |
| [2023-02-24 17:12:46,567][2343726] Updated weights for policy 0, policy_version 580 (0.0007) | |
| [2023-02-24 17:12:48,043][2343726] Updated weights for policy 0, policy_version 590 (0.0007) | |
| [2023-02-24 17:12:48,236][2343622] Fps is (10 sec: 27853.0, 60 sec: 27852.8, 300 sec: 26897.1). Total num frames: 2420736. Throughput: 0: 6946.0. Samples: 590410. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:12:48,236][2343622] Avg episode reward: [(0, '19.318')] | |
| [2023-02-24 17:12:48,236][2343698] Saving new best policy, reward=19.318! | |
| [2023-02-24 17:12:49,544][2343726] Updated weights for policy 0, policy_version 600 (0.0006) | |
| [2023-02-24 17:12:50,998][2343726] Updated weights for policy 0, policy_version 610 (0.0007) | |
| [2023-02-24 17:12:52,482][2343726] Updated weights for policy 0, policy_version 620 (0.0006) | |
| [2023-02-24 17:12:53,236][2343622] Fps is (10 sec: 27852.8, 60 sec: 27784.5, 300 sec: 26947.4). Total num frames: 2560000. Throughput: 0: 6928.7. Samples: 631860. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 17:12:53,236][2343622] Avg episode reward: [(0, '16.987')] | |
| [2023-02-24 17:12:53,955][2343726] Updated weights for policy 0, policy_version 630 (0.0007) | |
| [2023-02-24 17:12:55,438][2343726] Updated weights for policy 0, policy_version 640 (0.0007) | |
| [2023-02-24 17:12:56,905][2343726] Updated weights for policy 0, policy_version 650 (0.0007) | |
| [2023-02-24 17:12:58,236][2343622] Fps is (10 sec: 27852.8, 60 sec: 27716.3, 300 sec: 26992.6). Total num frames: 2699264. Throughput: 0: 6940.9. Samples: 673620. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-24 17:12:58,236][2343622] Avg episode reward: [(0, '17.090')] | |
| [2023-02-24 17:12:58,372][2343726] Updated weights for policy 0, policy_version 660 (0.0007) | |
| [2023-02-24 17:12:59,889][2343726] Updated weights for policy 0, policy_version 670 (0.0008) | |
| [2023-02-24 17:13:01,368][2343726] Updated weights for policy 0, policy_version 680 (0.0007) | |
| [2023-02-24 17:13:02,828][2343726] Updated weights for policy 0, policy_version 690 (0.0007) | |
| [2023-02-24 17:13:03,236][2343622] Fps is (10 sec: 27443.1, 60 sec: 27716.2, 300 sec: 26994.6). Total num frames: 2834432. Throughput: 0: 6933.1. Samples: 694028. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:13:03,236][2343622] Avg episode reward: [(0, '22.089')] | |
| [2023-02-24 17:13:03,240][2343698] Saving new best policy, reward=22.089! | |
| [2023-02-24 17:13:04,318][2343726] Updated weights for policy 0, policy_version 700 (0.0008) | |
| [2023-02-24 17:13:05,824][2343726] Updated weights for policy 0, policy_version 710 (0.0008) | |
| [2023-02-24 17:13:07,331][2343726] Updated weights for policy 0, policy_version 720 (0.0008) | |
| [2023-02-24 17:13:08,236][2343622] Fps is (10 sec: 27443.1, 60 sec: 27716.3, 300 sec: 27033.6). Total num frames: 2973696. Throughput: 0: 6930.7. Samples: 735420. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-24 17:13:08,236][2343622] Avg episode reward: [(0, '19.494')] | |
| [2023-02-24 17:13:08,793][2343726] Updated weights for policy 0, policy_version 730 (0.0007) | |
| [2023-02-24 17:13:10,279][2343726] Updated weights for policy 0, policy_version 740 (0.0007) | |
| [2023-02-24 17:13:11,813][2343726] Updated weights for policy 0, policy_version 750 (0.0007) | |
| [2023-02-24 17:13:13,236][2343622] Fps is (10 sec: 27443.2, 60 sec: 27716.3, 300 sec: 27033.6). Total num frames: 3108864. Throughput: 0: 6916.3. Samples: 776754. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-24 17:13:13,236][2343622] Avg episode reward: [(0, '20.543')] | |
| [2023-02-24 17:13:13,240][2343698] Saving /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000000759_3108864.pth... | |
| [2023-02-24 17:13:13,329][2343726] Updated weights for policy 0, policy_version 760 (0.0008) | |
| [2023-02-24 17:13:14,774][2343726] Updated weights for policy 0, policy_version 770 (0.0006) | |
| [2023-02-24 17:13:16,248][2343726] Updated weights for policy 0, policy_version 780 (0.0008) | |
| [2023-02-24 17:13:17,761][2343726] Updated weights for policy 0, policy_version 790 (0.0007) | |
| [2023-02-24 17:13:18,236][2343622] Fps is (10 sec: 27443.2, 60 sec: 27716.3, 300 sec: 27067.7). Total num frames: 3248128. Throughput: 0: 6906.6. Samples: 797394. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:13:18,236][2343622] Avg episode reward: [(0, '21.927')] | |
| [2023-02-24 17:13:19,279][2343726] Updated weights for policy 0, policy_version 800 (0.0007) | |
| [2023-02-24 17:13:20,759][2343726] Updated weights for policy 0, policy_version 810 (0.0007) | |
| [2023-02-24 17:13:22,276][2343726] Updated weights for policy 0, policy_version 820 (0.0007) | |
| [2023-02-24 17:13:23,236][2343622] Fps is (10 sec: 27443.3, 60 sec: 27648.0, 300 sec: 27066.4). Total num frames: 3383296. Throughput: 0: 6885.7. Samples: 838322. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2023-02-24 17:13:23,236][2343622] Avg episode reward: [(0, '22.487')] | |
| [2023-02-24 17:13:23,239][2343698] Saving new best policy, reward=22.487! | |
| [2023-02-24 17:13:23,768][2343726] Updated weights for policy 0, policy_version 830 (0.0007) | |
| [2023-02-24 17:13:25,246][2343726] Updated weights for policy 0, policy_version 840 (0.0007) | |
| [2023-02-24 17:13:26,742][2343726] Updated weights for policy 0, policy_version 850 (0.0007) | |
| [2023-02-24 17:13:28,236][2343622] Fps is (10 sec: 27034.0, 60 sec: 27579.8, 300 sec: 27065.1). Total num frames: 3518464. Throughput: 0: 6883.4. Samples: 879380. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2023-02-24 17:13:28,236][2343622] Avg episode reward: [(0, '22.399')] | |
| [2023-02-24 17:13:28,237][2343726] Updated weights for policy 0, policy_version 860 (0.0007) | |
| [2023-02-24 17:13:29,767][2343726] Updated weights for policy 0, policy_version 870 (0.0007) | |
| [2023-02-24 17:13:31,283][2343726] Updated weights for policy 0, policy_version 880 (0.0007) | |
| [2023-02-24 17:13:32,771][2343726] Updated weights for policy 0, policy_version 890 (0.0007) | |
| [2023-02-24 17:13:33,236][2343622] Fps is (10 sec: 27443.3, 60 sec: 27511.5, 300 sec: 27094.3). Total num frames: 3657728. Throughput: 0: 6874.0. Samples: 899738. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-24 17:13:33,236][2343622] Avg episode reward: [(0, '24.897')] | |
| [2023-02-24 17:13:33,239][2343698] Saving new best policy, reward=24.897! | |
| [2023-02-24 17:13:34,270][2343726] Updated weights for policy 0, policy_version 900 (0.0007) | |
| [2023-02-24 17:13:35,771][2343726] Updated weights for policy 0, policy_version 910 (0.0007) | |
| [2023-02-24 17:13:37,284][2343726] Updated weights for policy 0, policy_version 920 (0.0007) | |
| [2023-02-24 17:13:38,236][2343622] Fps is (10 sec: 27442.9, 60 sec: 27511.5, 300 sec: 27092.1). Total num frames: 3792896. Throughput: 0: 6862.1. Samples: 940656. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2023-02-24 17:13:38,236][2343622] Avg episode reward: [(0, '22.457')] | |
| [2023-02-24 17:13:38,783][2343726] Updated weights for policy 0, policy_version 930 (0.0007) | |
| [2023-02-24 17:13:40,263][2343726] Updated weights for policy 0, policy_version 940 (0.0007) | |
| [2023-02-24 17:13:41,748][2343726] Updated weights for policy 0, policy_version 950 (0.0007) | |
| [2023-02-24 17:13:43,236][2343622] Fps is (10 sec: 27033.6, 60 sec: 27443.2, 300 sec: 27090.1). Total num frames: 3928064. Throughput: 0: 6847.8. Samples: 981770. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-24 17:13:43,236][2343622] Avg episode reward: [(0, '21.833')] | |
| [2023-02-24 17:13:43,244][2343726] Updated weights for policy 0, policy_version 960 (0.0008) | |
| [2023-02-24 17:13:44,723][2343726] Updated weights for policy 0, policy_version 970 (0.0007) | |
| [2023-02-24 17:13:45,940][2343698] Stopping Batcher_0... | |
| [2023-02-24 17:13:45,941][2343698] Loop batcher_evt_loop terminating... | |
| [2023-02-24 17:13:45,941][2343698] Saving /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-24 17:13:45,945][2343622] Component Batcher_0 stopped! | |
| [2023-02-24 17:13:45,949][2343744] Stopping RolloutWorker_w1... | |
| [2023-02-24 17:13:45,949][2343745] Stopping RolloutWorker_w2... | |
| [2023-02-24 17:13:45,949][2343622] Component RolloutWorker_w2 stopped! | |
| [2023-02-24 17:13:45,949][2343622] Component RolloutWorker_w1 stopped! | |
| [2023-02-24 17:13:45,949][2343744] Loop rollout_proc1_evt_loop terminating... | |
| [2023-02-24 17:13:45,949][2343746] Stopping RolloutWorker_w4... | |
| [2023-02-24 17:13:45,949][2343750] Stopping RolloutWorker_w3... | |
| [2023-02-24 17:13:45,949][2343745] Loop rollout_proc2_evt_loop terminating... | |
| [2023-02-24 17:13:45,949][2343749] Stopping RolloutWorker_w5... | |
| [2023-02-24 17:13:45,950][2343622] Component RolloutWorker_w4 stopped! | |
| [2023-02-24 17:13:45,950][2343746] Loop rollout_proc4_evt_loop terminating... | |
| [2023-02-24 17:13:45,950][2343622] Component RolloutWorker_w3 stopped! | |
| [2023-02-24 17:13:45,950][2343749] Loop rollout_proc5_evt_loop terminating... | |
| [2023-02-24 17:13:45,950][2343750] Loop rollout_proc3_evt_loop terminating... | |
| [2023-02-24 17:13:45,950][2343622] Component RolloutWorker_w5 stopped! | |
| [2023-02-24 17:13:45,950][2343743] Stopping RolloutWorker_w0... | |
| [2023-02-24 17:13:45,950][2343622] Component RolloutWorker_w0 stopped! | |
| [2023-02-24 17:13:45,950][2343743] Loop rollout_proc0_evt_loop terminating... | |
| [2023-02-24 17:13:45,953][2343622] Component RolloutWorker_w7 stopped! | |
| [2023-02-24 17:13:45,953][2343747] Stopping RolloutWorker_w7... | |
| [2023-02-24 17:13:45,953][2343747] Loop rollout_proc7_evt_loop terminating... | |
| [2023-02-24 17:13:45,955][2343726] Weights refcount: 2 0 | |
| [2023-02-24 17:13:45,955][2343726] Stopping InferenceWorker_p0-w0... | |
| [2023-02-24 17:13:45,956][2343622] Component InferenceWorker_p0-w0 stopped! | |
| [2023-02-24 17:13:45,956][2343726] Loop inference_proc0-0_evt_loop terminating... | |
| [2023-02-24 17:13:46,004][2343748] Stopping RolloutWorker_w6... | |
| [2023-02-24 17:13:46,005][2343622] Component RolloutWorker_w6 stopped! | |
| [2023-02-24 17:13:46,005][2343748] Loop rollout_proc6_evt_loop terminating... | |
| [2023-02-24 17:13:46,008][2343698] Saving /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-24 17:13:46,105][2343698] Stopping LearnerWorker_p0... | |
| [2023-02-24 17:13:46,105][2343622] Component LearnerWorker_p0 stopped! | |
| [2023-02-24 17:13:46,106][2343698] Loop learner_proc0_evt_loop terminating... | |
| [2023-02-24 17:13:46,106][2343622] Waiting for process learner_proc0 to stop... | |
| [2023-02-24 17:13:46,712][2343622] Waiting for process inference_proc0-0 to join... | |
| [2023-02-24 17:13:46,712][2343622] Waiting for process rollout_proc0 to join... | |
| [2023-02-24 17:13:46,712][2343622] Waiting for process rollout_proc1 to join... | |
| [2023-02-24 17:13:46,712][2343622] Waiting for process rollout_proc2 to join... | |
| [2023-02-24 17:13:46,712][2343622] Waiting for process rollout_proc3 to join... | |
| [2023-02-24 17:13:46,712][2343622] Waiting for process rollout_proc4 to join... | |
| [2023-02-24 17:13:46,712][2343622] Waiting for process rollout_proc5 to join... | |
| [2023-02-24 17:13:46,713][2343622] Waiting for process rollout_proc6 to join... | |
| [2023-02-24 17:13:46,713][2343622] Waiting for process rollout_proc7 to join... | |
| [2023-02-24 17:13:46,713][2343622] Batcher 0 profile tree view: | |
| batching: 11.9572, releasing_batches: 0.0124 | |
| [2023-02-24 17:13:46,713][2343622] InferenceWorker_p0-w0 profile tree view: | |
| wait_policy: 0.0000 | |
| wait_policy_total: 2.9043 | |
| update_model: 2.1825 | |
| weight_update: 0.0007 | |
| one_step: 0.0019 | |
| handle_policy_step: 133.4731 | |
| deserialize: 6.2447, stack: 0.7828, obs_to_device_normalize: 34.7488, forward: 55.1577, send_messages: 9.6852 | |
| prepare_outputs: 21.4301 | |
| to_cpu: 14.6154 | |
| [2023-02-24 17:13:46,714][2343622] Learner 0 profile tree view: | |
| misc: 0.0029, prepare_batch: 6.2234 | |
| train: 18.9230 | |
| epoch_init: 0.0032, minibatch_init: 0.0035, losses_postprocess: 0.3250, kl_divergence: 0.1740, after_optimizer: 6.1827 | |
| calculate_losses: 6.6723 | |
| losses_init: 0.0020, forward_head: 0.5088, bptt_initial: 4.1259, tail: 0.3587, advantages_returns: 0.1020, losses: 0.7122 | |
| bptt: 0.7553 | |
| bptt_forward_core: 0.7253 | |
| update: 5.3342 | |
| clip: 0.8350 | |
| [2023-02-24 17:13:46,714][2343622] RolloutWorker_w0 profile tree view: | |
| wait_for_trajectories: 0.1049, enqueue_policy_requests: 5.6350, env_step: 81.8998, overhead: 6.8628, complete_rollouts: 0.1662 | |
| save_policy_outputs: 6.0304 | |
| split_output_tensors: 2.8870 | |
| [2023-02-24 17:13:46,714][2343622] RolloutWorker_w7 profile tree view: | |
| wait_for_trajectories: 0.1033, enqueue_policy_requests: 5.6327, env_step: 82.5081, overhead: 7.0028, complete_rollouts: 0.1684 | |
| save_policy_outputs: 6.1360 | |
| split_output_tensors: 2.9393 | |
| [2023-02-24 17:13:46,714][2343622] Loop Runner_EvtLoop terminating... | |
| [2023-02-24 17:13:46,714][2343622] Runner profile tree view: | |
| main_loop: 151.8999 | |
| [2023-02-24 17:13:46,715][2343622] Collected {0: 4005888}, FPS: 26371.9 | |
| [2023-02-24 17:32:32,877][2364708] Saving configuration to /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/config.json... | |
| [2023-02-24 17:32:32,878][2364708] Rollout worker 0 uses device cpu | |
| [2023-02-24 17:32:32,878][2364708] Rollout worker 1 uses device cpu | |
| [2023-02-24 17:32:32,878][2364708] Rollout worker 2 uses device cpu | |
| [2023-02-24 17:32:32,878][2364708] Rollout worker 3 uses device cpu | |
| [2023-02-24 17:32:32,878][2364708] Rollout worker 4 uses device cpu | |
| [2023-02-24 17:32:32,879][2364708] Rollout worker 5 uses device cpu | |
| [2023-02-24 17:32:32,879][2364708] Rollout worker 6 uses device cpu | |
| [2023-02-24 17:32:32,879][2364708] Rollout worker 7 uses device cpu | |
| [2023-02-24 17:32:32,879][2364708] Rollout worker 8 uses device cpu | |
| [2023-02-24 17:32:32,879][2364708] Rollout worker 9 uses device cpu | |
| [2023-02-24 17:32:32,879][2364708] Rollout worker 10 uses device cpu | |
| [2023-02-24 17:32:32,879][2364708] Rollout worker 11 uses device cpu | |
| [2023-02-24 17:32:32,879][2364708] Rollout worker 12 uses device cpu | |
| [2023-02-24 17:32:32,880][2364708] Rollout worker 13 uses device cpu | |
| [2023-02-24 17:32:32,880][2364708] Rollout worker 14 uses device cpu | |
| [2023-02-24 17:32:32,880][2364708] Rollout worker 15 uses device cpu | |
| [2023-02-24 17:32:32,936][2364708] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-24 17:32:32,936][2364708] InferenceWorker_p0-w0: min num requests: 5 | |
| [2023-02-24 17:32:32,970][2364708] Starting all processes... | |
| [2023-02-24 17:32:32,970][2364708] Starting process learner_proc0 | |
| [2023-02-24 17:32:33,717][2364708] Starting all processes... | |
| [2023-02-24 17:32:33,721][2364708] Starting process inference_proc0-0 | |
| [2023-02-24 17:32:33,721][2364708] Starting process rollout_proc0 | |
| [2023-02-24 17:32:33,721][2364708] Starting process rollout_proc1 | |
| [2023-02-24 17:32:33,722][2364791] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-24 17:32:33,722][2364791] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 | |
| [2023-02-24 17:32:33,721][2364708] Starting process rollout_proc2 | |
| [2023-02-24 17:32:33,721][2364708] Starting process rollout_proc3 | |
| [2023-02-24 17:32:33,721][2364708] Starting process rollout_proc4 | |
| [2023-02-24 17:32:33,722][2364708] Starting process rollout_proc5 | |
| [2023-02-24 17:32:33,722][2364708] Starting process rollout_proc6 | |
| [2023-02-24 17:32:33,723][2364708] Starting process rollout_proc7 | |
| [2023-02-24 17:32:33,726][2364708] Starting process rollout_proc8 | |
| [2023-02-24 17:32:33,727][2364708] Starting process rollout_proc9 | |
| [2023-02-24 17:32:33,739][2364791] Num visible devices: 1 | |
| [2023-02-24 17:32:33,728][2364708] Starting process rollout_proc10 | |
| [2023-02-24 17:32:33,729][2364708] Starting process rollout_proc11 | |
| [2023-02-24 17:32:33,729][2364708] Starting process rollout_proc12 | |
| [2023-02-24 17:32:33,729][2364708] Starting process rollout_proc13 | |
| [2023-02-24 17:32:33,796][2364791] Starting seed is not provided | |
| [2023-02-24 17:32:33,796][2364791] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-24 17:32:33,797][2364791] Initializing actor-critic model on device cuda:0 | |
| [2023-02-24 17:32:33,797][2364791] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-24 17:32:33,798][2364791] RunningMeanStd input shape: (1,) | |
| [2023-02-24 17:32:33,730][2364708] Starting process rollout_proc14 | |
| [2023-02-24 17:32:33,813][2364791] ConvEncoder: input_channels=3 | |
| [2023-02-24 17:32:34,006][2364791] Conv encoder output size: 512 | |
| [2023-02-24 17:32:34,023][2364791] Policy head output size: 512 | |
| [2023-02-24 17:32:34,038][2364791] Created Actor Critic model with architecture: | |
| [2023-02-24 17:32:34,050][2364791] ActorCriticSharedWeights( | |
| (obs_normalizer): ObservationNormalizer( | |
| (running_mean_std): RunningMeanStdDictInPlace( | |
| (running_mean_std): ModuleDict( | |
| (obs): RunningMeanStdInPlace() | |
| ) | |
| ) | |
| ) | |
| (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) | |
| (encoder): VizdoomEncoder( | |
| (basic_encoder): ConvEncoder( | |
| (enc): RecursiveScriptModule( | |
| original_name=ConvEncoderImpl | |
| (conv_head): RecursiveScriptModule( | |
| original_name=Sequential | |
| (0): RecursiveScriptModule(original_name=Conv2d) | |
| (1): RecursiveScriptModule(original_name=ELU) | |
| (2): RecursiveScriptModule(original_name=Conv2d) | |
| (3): RecursiveScriptModule(original_name=ELU) | |
| (4): RecursiveScriptModule(original_name=Conv2d) | |
| (5): RecursiveScriptModule(original_name=ELU) | |
| ) | |
| (mlp_layers): RecursiveScriptModule( | |
| original_name=Sequential | |
| (0): RecursiveScriptModule(original_name=Linear) | |
| (1): RecursiveScriptModule(original_name=ELU) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (core): ModelCoreRNN( | |
| (core): GRU(512, 512) | |
| ) | |
| (decoder): MlpDecoder( | |
| (mlp): Identity() | |
| ) | |
| (critic_linear): Linear(in_features=512, out_features=1, bias=True) | |
| (action_parameterization): ActionParameterizationDefault( | |
| (distribution_linear): Linear(in_features=512, out_features=5, bias=True) | |
| ) | |
| ) | |
| [2023-02-24 17:32:35,405][2364708] Starting process rollout_proc15 | |
| [2023-02-24 17:32:35,416][2364834] Worker 2 uses CPU cores [2] | |
| [2023-02-24 17:32:35,418][2364833] Worker 1 uses CPU cores [1] | |
| [2023-02-24 17:32:35,490][2364839] Worker 7 uses CPU cores [7] | |
| [2023-02-24 17:32:35,500][2364855] Worker 10 uses CPU cores [10] | |
| [2023-02-24 17:32:35,502][2364832] Worker 0 uses CPU cores [0] | |
| [2023-02-24 17:32:35,502][2364831] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-24 17:32:35,503][2364831] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 | |
| [2023-02-24 17:32:35,518][2364838] Worker 6 uses CPU cores [6] | |
| [2023-02-24 17:32:35,519][2364831] Num visible devices: 1 | |
| [2023-02-24 17:32:35,530][2364862] Worker 14 uses CPU cores [14] | |
| [2023-02-24 17:32:35,534][2364860] Worker 12 uses CPU cores [12] | |
| [2023-02-24 17:32:35,554][2364835] Worker 4 uses CPU cores [4] | |
| [2023-02-24 17:32:35,573][2364861] Worker 13 uses CPU cores [13] | |
| [2023-02-24 17:32:35,598][2364859] Worker 8 uses CPU cores [8] | |
| [2023-02-24 17:32:35,642][2364836] Worker 3 uses CPU cores [3] | |
| [2023-02-24 17:32:35,643][2364837] Worker 5 uses CPU cores [5] | |
| [2023-02-24 17:32:35,661][2364856] Worker 9 uses CPU cores [9] | |
| [2023-02-24 17:32:35,712][2364857] Worker 11 uses CPU cores [11] | |
| [2023-02-24 17:32:36,334][2365108] Worker 15 uses CPU cores [15] | |
| [2023-02-24 17:32:36,424][2364791] Using optimizer <class 'torch.optim.adam.Adam'> | |
| [2023-02-24 17:32:36,424][2364791] Loading state from checkpoint /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-24 17:32:36,444][2364791] Loading model from checkpoint | |
| [2023-02-24 17:32:36,447][2364791] Loaded experiment state at self.train_step=978, self.env_steps=4005888 | |
| [2023-02-24 17:32:36,447][2364791] Initialized policy 0 weights for model version 978 | |
| [2023-02-24 17:32:36,449][2364791] LearnerWorker_p0 finished initialization! | |
| [2023-02-24 17:32:36,449][2364791] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-24 17:32:36,525][2364831] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-24 17:32:36,525][2364831] RunningMeanStd input shape: (1,) | |
| [2023-02-24 17:32:36,532][2364831] ConvEncoder: input_channels=3 | |
| [2023-02-24 17:32:36,595][2364831] Conv encoder output size: 512 | |
| [2023-02-24 17:32:36,595][2364831] Policy head output size: 512 | |
| [2023-02-24 17:32:37,849][2364708] Inference worker 0-0 is ready! | |
| [2023-02-24 17:32:37,849][2364708] All inference workers are ready! Signal rollout workers to start! | |
| [2023-02-24 17:32:37,887][2364862] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:32:37,887][2364836] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:32:37,888][2364833] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:32:37,888][2364835] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:32:37,888][2364832] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:32:37,888][2364859] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:32:37,887][2364857] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:32:37,889][2364856] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:32:37,889][2364837] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:32:37,889][2365108] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:32:37,889][2364839] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:32:37,889][2364860] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:32:37,887][2364855] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:32:37,888][2364861] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:32:37,888][2364834] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:32:37,892][2364838] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:32:38,292][2364855] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:32:38,293][2364833] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:32:38,294][2364857] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:32:38,294][2364836] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:32:38,295][2364834] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:32:38,295][2364856] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:32:38,296][2364859] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:32:38,296][2364832] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:32:38,484][2364856] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:32:38,511][2364862] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:32:38,516][2364861] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:32:38,517][2364835] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:32:38,517][2364839] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:32:38,585][2364834] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:32:38,617][2364857] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:32:38,617][2364836] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:32:38,628][2364855] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:32:38,697][2364856] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:32:38,700][2364862] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:32:38,719][2364832] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:32:38,821][2364857] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:32:38,827][2364835] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:32:38,834][2364860] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:32:38,844][2364834] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:32:38,858][2364861] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:32:38,877][2364859] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:32:38,926][2364856] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:32:39,022][2364860] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:32:39,026][2364837] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:32:39,041][2364832] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:32:39,129][2365108] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:32:39,155][2364839] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:32:39,180][2364861] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:32:39,263][2364832] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:32:39,298][2364837] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:32:39,332][2364835] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:32:39,336][2364836] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:32:39,359][2364857] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:32:39,365][2364838] Decorrelating experience for 0 frames... | |
| [2023-02-24 17:32:39,378][2364834] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:32:39,523][2365108] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:32:39,535][2364833] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:32:39,552][2364862] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:32:39,593][2364857] Decorrelating experience for 128 frames... | |
| [2023-02-24 17:32:39,623][2364861] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:32:39,682][2364835] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:32:39,695][2364860] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:32:39,708][2364837] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:32:39,748][2364856] Decorrelating experience for 128 frames... | |
| [2023-02-24 17:32:39,783][2364862] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:32:39,789][2364832] Decorrelating experience for 128 frames... | |
| [2023-02-24 17:32:39,875][2364857] Decorrelating experience for 160 frames... | |
| [2023-02-24 17:32:39,884][2364855] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:32:39,898][2364861] Decorrelating experience for 128 frames... | |
| [2023-02-24 17:32:39,924][2364859] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:32:40,010][2364838] Decorrelating experience for 32 frames... | |
| [2023-02-24 17:32:40,043][2365108] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:32:40,047][2364856] Decorrelating experience for 160 frames... | |
| [2023-02-24 17:32:40,051][2364860] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:32:40,070][2364839] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:32:40,088][2364835] Decorrelating experience for 128 frames... | |
| [2023-02-24 17:32:40,123][2364834] Decorrelating experience for 128 frames... | |
| [2023-02-24 17:32:40,183][2364833] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:32:40,213][2364859] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:32:40,319][2364838] Decorrelating experience for 64 frames... | |
| [2023-02-24 17:32:40,333][2364835] Decorrelating experience for 160 frames... | |
| [2023-02-24 17:32:40,337][2364832] Decorrelating experience for 160 frames... | |
| [2023-02-24 17:32:40,372][2364862] Decorrelating experience for 128 frames... | |
| [2023-02-24 17:32:40,404][2364861] Decorrelating experience for 160 frames... | |
| [2023-02-24 17:32:40,429][2364837] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:32:40,514][2365108] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:32:40,535][2364839] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:32:40,595][2364834] Decorrelating experience for 160 frames... | |
| [2023-02-24 17:32:40,629][2364860] Decorrelating experience for 128 frames... | |
| [2023-02-24 17:32:40,640][2364833] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:32:40,643][2364859] Decorrelating experience for 128 frames... | |
| [2023-02-24 17:32:40,748][2364838] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:32:40,777][2365108] Decorrelating experience for 128 frames... | |
| [2023-02-24 17:32:40,793][2364836] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:32:40,912][2364837] Decorrelating experience for 128 frames... | |
| [2023-02-24 17:32:40,918][2364791] Signal inference workers to stop experience collection... | |
| [2023-02-24 17:32:40,922][2364831] InferenceWorker_p0-w0: stopping experience collection | |
| [2023-02-24 17:32:40,955][2364860] Decorrelating experience for 160 frames... | |
| [2023-02-24 17:32:40,971][2364859] Decorrelating experience for 160 frames... | |
| [2023-02-24 17:32:41,025][2364833] Decorrelating experience for 128 frames... | |
| [2023-02-24 17:32:41,056][2364836] Decorrelating experience for 128 frames... | |
| [2023-02-24 17:32:41,076][2364838] Decorrelating experience for 128 frames... | |
| [2023-02-24 17:32:41,132][2365108] Decorrelating experience for 160 frames... | |
| [2023-02-24 17:32:41,199][2364837] Decorrelating experience for 160 frames... | |
| [2023-02-24 17:32:41,202][2364862] Decorrelating experience for 160 frames... | |
| [2023-02-24 17:32:41,266][2364708] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 4005888. Throughput: 0: nan. Samples: 2304. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-02-24 17:32:41,266][2364708] Avg episode reward: [(0, '1.871')] | |
| [2023-02-24 17:32:41,343][2364839] Decorrelating experience for 128 frames... | |
| [2023-02-24 17:32:41,343][2364836] Decorrelating experience for 160 frames... | |
| [2023-02-24 17:32:41,392][2364838] Decorrelating experience for 160 frames... | |
| [2023-02-24 17:32:41,443][2364855] Decorrelating experience for 96 frames... | |
| [2023-02-24 17:32:41,569][2364833] Decorrelating experience for 160 frames... | |
| [2023-02-24 17:32:41,656][2364855] Decorrelating experience for 128 frames... | |
| [2023-02-24 17:32:41,671][2364839] Decorrelating experience for 160 frames... | |
| [2023-02-24 17:32:41,801][2364791] Signal inference workers to resume experience collection... | |
| [2023-02-24 17:32:41,801][2364831] InferenceWorker_p0-w0: resuming experience collection | |
| [2023-02-24 17:32:41,877][2364855] Decorrelating experience for 160 frames... | |
| [2023-02-24 17:32:43,213][2364831] Updated weights for policy 0, policy_version 988 (0.0223) | |
| [2023-02-24 17:32:44,160][2364831] Updated weights for policy 0, policy_version 998 (0.0009) | |
| [2023-02-24 17:32:45,129][2364831] Updated weights for policy 0, policy_version 1008 (0.0011) | |
| [2023-02-24 17:32:46,071][2364831] Updated weights for policy 0, policy_version 1018 (0.0009) | |
| [2023-02-24 17:32:46,266][2364708] Fps is (10 sec: 33586.6, 60 sec: 33586.6, 300 sec: 33586.6). Total num frames: 4173824. Throughput: 0: 3350.3. Samples: 19056. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2023-02-24 17:32:46,266][2364708] Avg episode reward: [(0, '18.870')] | |
| [2023-02-24 17:32:47,062][2364831] Updated weights for policy 0, policy_version 1028 (0.0009) | |
| [2023-02-24 17:32:48,070][2364831] Updated weights for policy 0, policy_version 1038 (0.0012) | |
| [2023-02-24 17:32:49,031][2364831] Updated weights for policy 0, policy_version 1048 (0.0009) | |
| [2023-02-24 17:32:50,044][2364831] Updated weights for policy 0, policy_version 1058 (0.0016) | |
| [2023-02-24 17:32:50,993][2364831] Updated weights for policy 0, policy_version 1068 (0.0013) | |
| [2023-02-24 17:32:51,266][2364708] Fps is (10 sec: 37683.0, 60 sec: 37683.0, 300 sec: 37683.0). Total num frames: 4382720. Throughput: 0: 7973.1. Samples: 82035. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0) | |
| [2023-02-24 17:32:51,266][2364708] Avg episode reward: [(0, '24.692')] | |
| [2023-02-24 17:32:51,978][2364831] Updated weights for policy 0, policy_version 1078 (0.0010) | |
| [2023-02-24 17:32:52,932][2364708] Heartbeat connected on Batcher_0 | |
| [2023-02-24 17:32:52,934][2364708] Heartbeat connected on LearnerWorker_p0 | |
| [2023-02-24 17:32:52,941][2364708] Heartbeat connected on InferenceWorker_p0-w0 | |
| [2023-02-24 17:32:52,944][2364708] Heartbeat connected on RolloutWorker_w2 | |
| [2023-02-24 17:32:52,945][2364708] Heartbeat connected on RolloutWorker_w3 | |
| [2023-02-24 17:32:52,949][2364708] Heartbeat connected on RolloutWorker_w4 | |
| [2023-02-24 17:32:52,949][2364708] Heartbeat connected on RolloutWorker_w5 | |
| [2023-02-24 17:32:52,953][2364708] Heartbeat connected on RolloutWorker_w6 | |
| [2023-02-24 17:32:52,953][2364708] Heartbeat connected on RolloutWorker_w7 | |
| [2023-02-24 17:32:52,955][2364708] Heartbeat connected on RolloutWorker_w0 | |
| [2023-02-24 17:32:52,955][2364708] Heartbeat connected on RolloutWorker_w1 | |
| [2023-02-24 17:32:52,957][2364708] Heartbeat connected on RolloutWorker_w8 | |
| [2023-02-24 17:32:52,958][2364708] Heartbeat connected on RolloutWorker_w9 | |
| [2023-02-24 17:32:52,962][2364708] Heartbeat connected on RolloutWorker_w10 | |
| [2023-02-24 17:32:52,963][2364708] Heartbeat connected on RolloutWorker_w11 | |
| [2023-02-24 17:32:52,966][2364708] Heartbeat connected on RolloutWorker_w13 | |
| [2023-02-24 17:32:52,967][2364708] Heartbeat connected on RolloutWorker_w12 | |
| [2023-02-24 17:32:52,968][2364708] Heartbeat connected on RolloutWorker_w14 | |
| [2023-02-24 17:32:52,981][2364708] Heartbeat connected on RolloutWorker_w15 | |
| [2023-02-24 17:32:52,981][2364831] Updated weights for policy 0, policy_version 1088 (0.0012) | |
| [2023-02-24 17:32:53,959][2364831] Updated weights for policy 0, policy_version 1098 (0.0010) | |
| [2023-02-24 17:32:54,954][2364831] Updated weights for policy 0, policy_version 1108 (0.0009) | |
| [2023-02-24 17:32:55,930][2364831] Updated weights for policy 0, policy_version 1118 (0.0011) | |
| [2023-02-24 17:32:56,266][2364708] Fps is (10 sec: 41779.4, 60 sec: 39048.4, 300 sec: 39048.4). Total num frames: 4591616. Throughput: 0: 9485.2. Samples: 144582. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2023-02-24 17:32:56,266][2364708] Avg episode reward: [(0, '25.204')] | |
| [2023-02-24 17:32:56,266][2364791] Saving new best policy, reward=25.204! | |
| [2023-02-24 17:32:56,911][2364831] Updated weights for policy 0, policy_version 1128 (0.0014) | |
| [2023-02-24 17:32:57,948][2364831] Updated weights for policy 0, policy_version 1138 (0.0011) | |
| [2023-02-24 17:32:58,912][2364831] Updated weights for policy 0, policy_version 1148 (0.0011) | |
| [2023-02-24 17:32:59,887][2364831] Updated weights for policy 0, policy_version 1158 (0.0012) | |
| [2023-02-24 17:33:00,871][2364831] Updated weights for policy 0, policy_version 1168 (0.0016) | |
| [2023-02-24 17:33:01,266][2364708] Fps is (10 sec: 41369.3, 60 sec: 39526.2, 300 sec: 39526.2). Total num frames: 4796416. Throughput: 0: 8660.6. Samples: 175518. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0) | |
| [2023-02-24 17:33:01,266][2364708] Avg episode reward: [(0, '24.312')] | |
| [2023-02-24 17:33:01,888][2364831] Updated weights for policy 0, policy_version 1178 (0.0009) | |
| [2023-02-24 17:33:02,860][2364831] Updated weights for policy 0, policy_version 1188 (0.0009) | |
| [2023-02-24 17:33:03,875][2364831] Updated weights for policy 0, policy_version 1198 (0.0014) | |
| [2023-02-24 17:33:04,853][2364831] Updated weights for policy 0, policy_version 1208 (0.0009) | |
| [2023-02-24 17:33:05,857][2364831] Updated weights for policy 0, policy_version 1218 (0.0012) | |
| [2023-02-24 17:33:06,266][2364708] Fps is (10 sec: 41368.6, 60 sec: 39976.5, 300 sec: 39976.5). Total num frames: 5005312. Throughput: 0: 9410.3. Samples: 237564. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2023-02-24 17:33:06,266][2364708] Avg episode reward: [(0, '24.517')] | |
| [2023-02-24 17:33:06,796][2364831] Updated weights for policy 0, policy_version 1228 (0.0011) | |
| [2023-02-24 17:33:07,774][2364831] Updated weights for policy 0, policy_version 1238 (0.0011) | |
| [2023-02-24 17:33:08,779][2364831] Updated weights for policy 0, policy_version 1248 (0.0012) | |
| [2023-02-24 17:33:09,772][2364831] Updated weights for policy 0, policy_version 1258 (0.0010) | |
| [2023-02-24 17:33:10,736][2364831] Updated weights for policy 0, policy_version 1268 (0.0014) | |
| [2023-02-24 17:33:11,266][2364708] Fps is (10 sec: 41779.2, 60 sec: 40277.2, 300 sec: 40277.2). Total num frames: 5214208. Throughput: 0: 9920.8. Samples: 299928. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2023-02-24 17:33:11,266][2364708] Avg episode reward: [(0, '30.044')] | |
| [2023-02-24 17:33:11,269][2364791] Saving new best policy, reward=30.044! | |
| [2023-02-24 17:33:11,776][2364831] Updated weights for policy 0, policy_version 1278 (0.0009) | |
| [2023-02-24 17:33:12,732][2364831] Updated weights for policy 0, policy_version 1288 (0.0009) | |
| [2023-02-24 17:33:13,718][2364831] Updated weights for policy 0, policy_version 1298 (0.0014) | |
| [2023-02-24 17:33:14,743][2364831] Updated weights for policy 0, policy_version 1308 (0.0011) | |
| [2023-02-24 17:33:15,710][2364831] Updated weights for policy 0, policy_version 1318 (0.0012) | |
| [2023-02-24 17:33:16,266][2364708] Fps is (10 sec: 41370.3, 60 sec: 40374.7, 300 sec: 40374.7). Total num frames: 5419008. Throughput: 0: 9385.3. Samples: 330789. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2023-02-24 17:33:16,266][2364708] Avg episode reward: [(0, '26.183')] | |
| [2023-02-24 17:33:16,724][2364831] Updated weights for policy 0, policy_version 1328 (0.0008) | |
| [2023-02-24 17:33:17,710][2364831] Updated weights for policy 0, policy_version 1338 (0.0014) | |
| [2023-02-24 17:33:18,666][2364831] Updated weights for policy 0, policy_version 1348 (0.0009) | |
| [2023-02-24 17:33:19,683][2364831] Updated weights for policy 0, policy_version 1358 (0.0009) | |
| [2023-02-24 17:33:20,617][2364831] Updated weights for policy 0, policy_version 1368 (0.0010) | |
| [2023-02-24 17:33:21,266][2364708] Fps is (10 sec: 41370.0, 60 sec: 40550.4, 300 sec: 40550.4). Total num frames: 5627904. Throughput: 0: 9770.6. Samples: 393129. Policy #0 lag: (min: 1.0, avg: 2.0, max: 4.0) | |
| [2023-02-24 17:33:21,266][2364708] Avg episode reward: [(0, '25.398')] | |
| [2023-02-24 17:33:21,637][2364831] Updated weights for policy 0, policy_version 1378 (0.0009) | |
| [2023-02-24 17:33:22,601][2364831] Updated weights for policy 0, policy_version 1388 (0.0012) | |
| [2023-02-24 17:33:23,610][2364831] Updated weights for policy 0, policy_version 1398 (0.0009) | |
| [2023-02-24 17:33:24,587][2364831] Updated weights for policy 0, policy_version 1408 (0.0012) | |
| [2023-02-24 17:33:25,585][2364831] Updated weights for policy 0, policy_version 1418 (0.0010) | |
| [2023-02-24 17:33:26,266][2364708] Fps is (10 sec: 41369.7, 60 sec: 40595.8, 300 sec: 40595.8). Total num frames: 5832704. Throughput: 0: 10069.7. Samples: 455439. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0) | |
| [2023-02-24 17:33:26,266][2364708] Avg episode reward: [(0, '24.553')] | |
| [2023-02-24 17:33:26,570][2364831] Updated weights for policy 0, policy_version 1428 (0.0009) | |
| [2023-02-24 17:33:27,565][2364831] Updated weights for policy 0, policy_version 1438 (0.0009) | |
| [2023-02-24 17:33:28,519][2364831] Updated weights for policy 0, policy_version 1448 (0.0012) | |
| [2023-02-24 17:33:29,541][2364831] Updated weights for policy 0, policy_version 1458 (0.0011) | |
| [2023-02-24 17:33:30,518][2364831] Updated weights for policy 0, policy_version 1468 (0.0012) | |
| [2023-02-24 17:33:31,266][2364708] Fps is (10 sec: 41369.0, 60 sec: 40714.1, 300 sec: 40714.1). Total num frames: 6041600. Throughput: 0: 10387.5. Samples: 486495. Policy #0 lag: (min: 0.0, avg: 2.1, max: 5.0) | |
| [2023-02-24 17:33:31,266][2364708] Avg episode reward: [(0, '27.755')] | |
| [2023-02-24 17:33:31,537][2364831] Updated weights for policy 0, policy_version 1478 (0.0009) | |
| [2023-02-24 17:33:32,488][2364831] Updated weights for policy 0, policy_version 1488 (0.0009) | |
| [2023-02-24 17:33:33,488][2364831] Updated weights for policy 0, policy_version 1498 (0.0010) | |
| [2023-02-24 17:33:34,494][2364831] Updated weights for policy 0, policy_version 1508 (0.0009) | |
| [2023-02-24 17:33:35,471][2364831] Updated weights for policy 0, policy_version 1518 (0.0012) | |
| [2023-02-24 17:33:36,266][2364708] Fps is (10 sec: 41368.5, 60 sec: 40736.3, 300 sec: 40736.3). Total num frames: 6246400. Throughput: 0: 10367.1. Samples: 548559. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0) | |
| [2023-02-24 17:33:36,267][2364708] Avg episode reward: [(0, '29.595')] | |
| [2023-02-24 17:33:36,445][2364831] Updated weights for policy 0, policy_version 1528 (0.0015) | |
| [2023-02-24 17:33:37,457][2364831] Updated weights for policy 0, policy_version 1538 (0.0010) | |
| [2023-02-24 17:33:38,386][2364831] Updated weights for policy 0, policy_version 1548 (0.0010) | |
| [2023-02-24 17:33:39,394][2364831] Updated weights for policy 0, policy_version 1558 (0.0009) | |
| [2023-02-24 17:33:40,414][2364831] Updated weights for policy 0, policy_version 1568 (0.0013) | |
| [2023-02-24 17:33:41,266][2364708] Fps is (10 sec: 41779.5, 60 sec: 40891.7, 300 sec: 40891.7). Total num frames: 6459392. Throughput: 0: 10363.3. Samples: 610929. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2023-02-24 17:33:41,266][2364708] Avg episode reward: [(0, '27.467')] | |
| [2023-02-24 17:33:41,392][2364831] Updated weights for policy 0, policy_version 1578 (0.0011) | |
| [2023-02-24 17:33:42,409][2364831] Updated weights for policy 0, policy_version 1588 (0.0015) | |
| [2023-02-24 17:33:43,364][2364831] Updated weights for policy 0, policy_version 1598 (0.0016) | |
| [2023-02-24 17:33:44,391][2364831] Updated weights for policy 0, policy_version 1608 (0.0009) | |
| [2023-02-24 17:33:45,344][2364831] Updated weights for policy 0, policy_version 1618 (0.0009) | |
| [2023-02-24 17:33:46,266][2364708] Fps is (10 sec: 41371.0, 60 sec: 41437.9, 300 sec: 40834.0). Total num frames: 6660096. Throughput: 0: 10362.0. Samples: 641805. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2023-02-24 17:33:46,266][2364708] Avg episode reward: [(0, '26.443')] | |
| [2023-02-24 17:33:46,345][2364831] Updated weights for policy 0, policy_version 1628 (0.0009) | |
| [2023-02-24 17:33:47,361][2364831] Updated weights for policy 0, policy_version 1638 (0.0012) | |
| [2023-02-24 17:33:48,358][2364831] Updated weights for policy 0, policy_version 1648 (0.0015) | |
| [2023-02-24 17:33:49,372][2364831] Updated weights for policy 0, policy_version 1658 (0.0010) | |
| [2023-02-24 17:33:50,384][2364831] Updated weights for policy 0, policy_version 1668 (0.0009) | |
| [2023-02-24 17:33:51,266][2364708] Fps is (10 sec: 40550.3, 60 sec: 41369.5, 300 sec: 40842.9). Total num frames: 6864896. Throughput: 0: 10346.7. Samples: 703164. Policy #0 lag: (min: 0.0, avg: 1.9, max: 5.0) | |
| [2023-02-24 17:33:51,266][2364708] Avg episode reward: [(0, '29.470')] | |
| [2023-02-24 17:33:51,339][2364831] Updated weights for policy 0, policy_version 1678 (0.0009) | |
| [2023-02-24 17:33:52,333][2364831] Updated weights for policy 0, policy_version 1688 (0.0013) | |
| [2023-02-24 17:33:53,373][2364831] Updated weights for policy 0, policy_version 1698 (0.0010) | |
| [2023-02-24 17:33:54,326][2364831] Updated weights for policy 0, policy_version 1708 (0.0011) | |
| [2023-02-24 17:33:55,317][2364831] Updated weights for policy 0, policy_version 1718 (0.0015) | |
| [2023-02-24 17:33:56,266][2364708] Fps is (10 sec: 41369.2, 60 sec: 41369.5, 300 sec: 40905.3). Total num frames: 7073792. Throughput: 0: 10341.1. Samples: 765279. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0) | |
| [2023-02-24 17:33:56,266][2364708] Avg episode reward: [(0, '29.662')] | |
| [2023-02-24 17:33:56,319][2364831] Updated weights for policy 0, policy_version 1728 (0.0009) | |
| [2023-02-24 17:33:57,289][2364831] Updated weights for policy 0, policy_version 1738 (0.0014) | |
| [2023-02-24 17:33:58,346][2364831] Updated weights for policy 0, policy_version 1748 (0.0009) | |
| [2023-02-24 17:33:59,308][2364831] Updated weights for policy 0, policy_version 1758 (0.0009) | |
| [2023-02-24 17:34:00,266][2364831] Updated weights for policy 0, policy_version 1768 (0.0009) | |
| [2023-02-24 17:34:01,266][2364708] Fps is (10 sec: 41369.7, 60 sec: 41369.6, 300 sec: 40908.7). Total num frames: 7278592. Throughput: 0: 10343.3. Samples: 796236. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0) | |
| [2023-02-24 17:34:01,266][2364708] Avg episode reward: [(0, '28.381')] | |
| [2023-02-24 17:34:01,272][2364831] Updated weights for policy 0, policy_version 1778 (0.0014) | |
| [2023-02-24 17:34:02,285][2364831] Updated weights for policy 0, policy_version 1788 (0.0012) | |
| [2023-02-24 17:34:03,229][2364831] Updated weights for policy 0, policy_version 1798 (0.0014) | |
| [2023-02-24 17:34:04,225][2364831] Updated weights for policy 0, policy_version 1808 (0.0011) | |
| [2023-02-24 17:34:05,252][2364831] Updated weights for policy 0, policy_version 1818 (0.0011) | |
| [2023-02-24 17:34:06,217][2364831] Updated weights for policy 0, policy_version 1828 (0.0014) | |
| [2023-02-24 17:34:06,266][2364708] Fps is (10 sec: 41370.1, 60 sec: 41369.8, 300 sec: 40960.0). Total num frames: 7487488. Throughput: 0: 10333.9. Samples: 858156. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2023-02-24 17:34:06,266][2364708] Avg episode reward: [(0, '28.723')] | |
| [2023-02-24 17:34:07,238][2364831] Updated weights for policy 0, policy_version 1838 (0.0012) | |
| [2023-02-24 17:34:08,199][2364831] Updated weights for policy 0, policy_version 1848 (0.0009) | |
| [2023-02-24 17:34:09,209][2364831] Updated weights for policy 0, policy_version 1858 (0.0015) | |
| [2023-02-24 17:34:10,200][2364831] Updated weights for policy 0, policy_version 1868 (0.0013) | |
| [2023-02-24 17:34:11,160][2364831] Updated weights for policy 0, policy_version 1878 (0.0012) | |
| [2023-02-24 17:34:11,266][2364708] Fps is (10 sec: 41370.0, 60 sec: 41301.4, 300 sec: 40960.0). Total num frames: 7692288. Throughput: 0: 10328.4. Samples: 920217. Policy #0 lag: (min: 0.0, avg: 1.6, max: 3.0) | |
| [2023-02-24 17:34:11,266][2364708] Avg episode reward: [(0, '27.028')] | |
| [2023-02-24 17:34:12,189][2364831] Updated weights for policy 0, policy_version 1888 (0.0013) | |
| [2023-02-24 17:34:13,157][2364831] Updated weights for policy 0, policy_version 1898 (0.0009) | |
| [2023-02-24 17:34:14,140][2364831] Updated weights for policy 0, policy_version 1908 (0.0009) | |
| [2023-02-24 17:34:15,142][2364831] Updated weights for policy 0, policy_version 1918 (0.0009) | |
| [2023-02-24 17:34:16,149][2364831] Updated weights for policy 0, policy_version 1928 (0.0008) | |
| [2023-02-24 17:34:16,266][2364708] Fps is (10 sec: 41368.9, 60 sec: 41369.6, 300 sec: 41003.1). Total num frames: 7901184. Throughput: 0: 10329.2. Samples: 951309. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2023-02-24 17:34:16,266][2364708] Avg episode reward: [(0, '31.603')] | |
| [2023-02-24 17:34:16,267][2364791] Saving new best policy, reward=31.603! | |
| [2023-02-24 17:34:17,141][2364831] Updated weights for policy 0, policy_version 1938 (0.0011) | |
| [2023-02-24 17:34:18,125][2364831] Updated weights for policy 0, policy_version 1948 (0.0010) | |
| [2023-02-24 17:34:19,131][2364831] Updated weights for policy 0, policy_version 1958 (0.0012) | |
| [2023-02-24 17:34:20,142][2364831] Updated weights for policy 0, policy_version 1968 (0.0009) | |
| [2023-02-24 17:34:21,131][2364831] Updated weights for policy 0, policy_version 1978 (0.0014) | |
| [2023-02-24 17:34:21,266][2364708] Fps is (10 sec: 41369.1, 60 sec: 41301.3, 300 sec: 41000.9). Total num frames: 8105984. Throughput: 0: 10320.3. Samples: 1012971. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2023-02-24 17:34:21,266][2364708] Avg episode reward: [(0, '28.359')] | |
| [2023-02-24 17:34:22,137][2364831] Updated weights for policy 0, policy_version 1988 (0.0009) | |
| [2023-02-24 17:34:23,105][2364831] Updated weights for policy 0, policy_version 1998 (0.0009) | |
| [2023-02-24 17:34:24,115][2364831] Updated weights for policy 0, policy_version 2008 (0.0012) | |
| [2023-02-24 17:34:25,058][2364831] Updated weights for policy 0, policy_version 2018 (0.0010) | |
| [2023-02-24 17:34:26,094][2364831] Updated weights for policy 0, policy_version 2028 (0.0010) | |
| [2023-02-24 17:34:26,266][2364708] Fps is (10 sec: 41369.7, 60 sec: 41369.6, 300 sec: 41038.0). Total num frames: 8314880. Throughput: 0: 10310.5. Samples: 1074903. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2023-02-24 17:34:26,266][2364708] Avg episode reward: [(0, '28.710')] | |
| [2023-02-24 17:34:27,060][2364831] Updated weights for policy 0, policy_version 2038 (0.0011) | |
| [2023-02-24 17:34:28,047][2364831] Updated weights for policy 0, policy_version 2048 (0.0013) | |
| [2023-02-24 17:34:29,023][2364831] Updated weights for policy 0, policy_version 2058 (0.0009) | |
| [2023-02-24 17:34:30,021][2364831] Updated weights for policy 0, policy_version 2068 (0.0012) | |
| [2023-02-24 17:34:31,055][2364831] Updated weights for policy 0, policy_version 2078 (0.0009) | |
| [2023-02-24 17:34:31,266][2364708] Fps is (10 sec: 41369.6, 60 sec: 41301.4, 300 sec: 41034.4). Total num frames: 8519680. Throughput: 0: 10314.6. Samples: 1105962. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2023-02-24 17:34:31,266][2364708] Avg episode reward: [(0, '32.526')] | |
| [2023-02-24 17:34:31,271][2364791] Saving /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000002080_8519680.pth... | |
| [2023-02-24 17:34:31,337][2364791] Removing /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000000759_3108864.pth | |
| [2023-02-24 17:34:31,343][2364791] Saving new best policy, reward=32.526! | |
| [2023-02-24 17:34:32,027][2364831] Updated weights for policy 0, policy_version 2088 (0.0014) | |
| [2023-02-24 17:34:33,002][2364831] Updated weights for policy 0, policy_version 2098 (0.0011) | |
| [2023-02-24 17:34:34,028][2364831] Updated weights for policy 0, policy_version 2108 (0.0010) | |
| [2023-02-24 17:34:34,994][2364831] Updated weights for policy 0, policy_version 2118 (0.0009) | |
| [2023-02-24 17:34:36,021][2364831] Updated weights for policy 0, policy_version 2128 (0.0011) | |
| [2023-02-24 17:34:36,266][2364708] Fps is (10 sec: 40960.1, 60 sec: 41301.5, 300 sec: 41031.2). Total num frames: 8724480. Throughput: 0: 10328.4. Samples: 1167942. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2023-02-24 17:34:36,266][2364708] Avg episode reward: [(0, '29.338')] | |
| [2023-02-24 17:34:37,019][2364831] Updated weights for policy 0, policy_version 2138 (0.0012) | |
| [2023-02-24 17:34:38,029][2364831] Updated weights for policy 0, policy_version 2148 (0.0010) | |
| [2023-02-24 17:34:38,999][2364831] Updated weights for policy 0, policy_version 2158 (0.0009) | |
| [2023-02-24 17:34:40,008][2364831] Updated weights for policy 0, policy_version 2168 (0.0009) | |
| [2023-02-24 17:34:40,960][2364831] Updated weights for policy 0, policy_version 2178 (0.0013) | |
| [2023-02-24 17:34:41,266][2364708] Fps is (10 sec: 40960.0, 60 sec: 41164.8, 300 sec: 41028.2). Total num frames: 8929280. Throughput: 0: 10315.9. Samples: 1229496. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2023-02-24 17:34:41,266][2364708] Avg episode reward: [(0, '28.569')] | |
| [2023-02-24 17:34:41,985][2364831] Updated weights for policy 0, policy_version 2188 (0.0012) | |
| [2023-02-24 17:34:42,962][2364831] Updated weights for policy 0, policy_version 2198 (0.0009) | |
| [2023-02-24 17:34:43,968][2364831] Updated weights for policy 0, policy_version 2208 (0.0009) | |
| [2023-02-24 17:34:44,995][2364831] Updated weights for policy 0, policy_version 2218 (0.0010) | |
| [2023-02-24 17:34:45,933][2364831] Updated weights for policy 0, policy_version 2228 (0.0010) | |
| [2023-02-24 17:34:46,266][2364708] Fps is (10 sec: 41369.4, 60 sec: 41301.2, 300 sec: 41058.3). Total num frames: 9138176. Throughput: 0: 10313.9. Samples: 1260363. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2023-02-24 17:34:46,266][2364708] Avg episode reward: [(0, '29.705')] | |
| [2023-02-24 17:34:46,949][2364831] Updated weights for policy 0, policy_version 2238 (0.0011) | |
| [2023-02-24 17:34:47,940][2364831] Updated weights for policy 0, policy_version 2248 (0.0012) | |
| [2023-02-24 17:34:48,931][2364831] Updated weights for policy 0, policy_version 2258 (0.0016) | |
| [2023-02-24 17:34:49,903][2364831] Updated weights for policy 0, policy_version 2268 (0.0015) | |
| [2023-02-24 17:34:50,883][2364831] Updated weights for policy 0, policy_version 2278 (0.0009) | |
| [2023-02-24 17:34:51,266][2364708] Fps is (10 sec: 41369.7, 60 sec: 41301.4, 300 sec: 41054.5). Total num frames: 9342976. Throughput: 0: 10311.3. Samples: 1322166. Policy #0 lag: (min: 0.0, avg: 1.6, max: 4.0) | |
| [2023-02-24 17:34:51,266][2364708] Avg episode reward: [(0, '30.602')] | |
| [2023-02-24 17:34:51,902][2364831] Updated weights for policy 0, policy_version 2288 (0.0010) | |
| [2023-02-24 17:34:52,909][2364831] Updated weights for policy 0, policy_version 2298 (0.0010) | |
| [2023-02-24 17:34:53,904][2364831] Updated weights for policy 0, policy_version 2308 (0.0010) | |
| [2023-02-24 17:34:54,860][2364831] Updated weights for policy 0, policy_version 2318 (0.0010) | |
| [2023-02-24 17:34:55,858][2364831] Updated weights for policy 0, policy_version 2328 (0.0009) | |
| [2023-02-24 17:34:56,266][2364708] Fps is (10 sec: 40960.2, 60 sec: 41233.1, 300 sec: 41051.0). Total num frames: 9547776. Throughput: 0: 10311.1. Samples: 1384218. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2023-02-24 17:34:56,266][2364708] Avg episode reward: [(0, '29.322')] | |
| [2023-02-24 17:34:56,865][2364831] Updated weights for policy 0, policy_version 2338 (0.0009) | |
| [2023-02-24 17:34:57,857][2364831] Updated weights for policy 0, policy_version 2348 (0.0009) | |
| [2023-02-24 17:34:58,810][2364831] Updated weights for policy 0, policy_version 2358 (0.0016) | |
| [2023-02-24 17:34:59,854][2364831] Updated weights for policy 0, policy_version 2368 (0.0012) | |
| [2023-02-24 17:35:00,835][2364831] Updated weights for policy 0, policy_version 2378 (0.0009) | |
| [2023-02-24 17:35:01,266][2364708] Fps is (10 sec: 41369.5, 60 sec: 41301.3, 300 sec: 41077.0). Total num frames: 9756672. Throughput: 0: 10308.8. Samples: 1415205. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0) | |
| [2023-02-24 17:35:01,266][2364708] Avg episode reward: [(0, '30.241')] | |
| [2023-02-24 17:35:01,804][2364831] Updated weights for policy 0, policy_version 2388 (0.0012) | |
| [2023-02-24 17:35:02,822][2364831] Updated weights for policy 0, policy_version 2398 (0.0010) | |
| [2023-02-24 17:35:03,814][2364831] Updated weights for policy 0, policy_version 2408 (0.0010) | |
| [2023-02-24 17:35:04,799][2364831] Updated weights for policy 0, policy_version 2418 (0.0011) | |
| [2023-02-24 17:35:05,796][2364831] Updated weights for policy 0, policy_version 2428 (0.0009) | |
| [2023-02-24 17:35:06,266][2364708] Fps is (10 sec: 41369.5, 60 sec: 41233.0, 300 sec: 41073.0). Total num frames: 9961472. Throughput: 0: 10314.6. Samples: 1477128. Policy #0 lag: (min: 0.0, avg: 2.2, max: 4.0) | |
| [2023-02-24 17:35:06,266][2364708] Avg episode reward: [(0, '26.511')] | |
| [2023-02-24 17:35:06,791][2364831] Updated weights for policy 0, policy_version 2438 (0.0012) | |
| [2023-02-24 17:35:07,790][2364831] Updated weights for policy 0, policy_version 2448 (0.0009) | |
| [2023-02-24 17:35:08,780][2364831] Updated weights for policy 0, policy_version 2458 (0.0014) | |
| [2023-02-24 17:35:09,752][2364831] Updated weights for policy 0, policy_version 2468 (0.0010) | |
| [2023-02-24 17:35:10,772][2364831] Updated weights for policy 0, policy_version 2478 (0.0010) | |
| [2023-02-24 17:35:11,266][2364708] Fps is (10 sec: 40958.9, 60 sec: 41232.8, 300 sec: 41069.1). Total num frames: 10166272. Throughput: 0: 10309.2. Samples: 1538820. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0) | |
| [2023-02-24 17:35:11,267][2364708] Avg episode reward: [(0, '31.927')] | |
| [2023-02-24 17:35:11,766][2364831] Updated weights for policy 0, policy_version 2488 (0.0012) | |
| [2023-02-24 17:35:12,753][2364831] Updated weights for policy 0, policy_version 2498 (0.0011) | |
| [2023-02-24 17:35:13,754][2364831] Updated weights for policy 0, policy_version 2508 (0.0014) | |
| [2023-02-24 17:35:14,735][2364831] Updated weights for policy 0, policy_version 2518 (0.0013) | |
| [2023-02-24 17:35:15,703][2364831] Updated weights for policy 0, policy_version 2528 (0.0011) | |
| [2023-02-24 17:35:16,266][2364708] Fps is (10 sec: 41370.2, 60 sec: 41233.2, 300 sec: 41092.1). Total num frames: 10375168. Throughput: 0: 10308.7. Samples: 1569852. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2023-02-24 17:35:16,266][2364708] Avg episode reward: [(0, '29.333')] | |
| [2023-02-24 17:35:16,713][2364831] Updated weights for policy 0, policy_version 2538 (0.0012) | |
| [2023-02-24 17:35:17,728][2364831] Updated weights for policy 0, policy_version 2548 (0.0009) | |
| [2023-02-24 17:35:18,681][2364831] Updated weights for policy 0, policy_version 2558 (0.0012) | |
| [2023-02-24 17:35:19,719][2364831] Updated weights for policy 0, policy_version 2568 (0.0008) | |
| [2023-02-24 17:35:20,725][2364831] Updated weights for policy 0, policy_version 2578 (0.0010) | |
| [2023-02-24 17:35:21,266][2364708] Fps is (10 sec: 41370.6, 60 sec: 41233.1, 300 sec: 41088.0). Total num frames: 10579968. Throughput: 0: 10308.5. Samples: 1631826. Policy #0 lag: (min: 0.0, avg: 1.4, max: 3.0) | |
| [2023-02-24 17:35:21,266][2364708] Avg episode reward: [(0, '29.221')] | |
| [2023-02-24 17:35:21,646][2364831] Updated weights for policy 0, policy_version 2588 (0.0013) | |
| [2023-02-24 17:35:22,678][2364831] Updated weights for policy 0, policy_version 2598 (0.0011) | |
| [2023-02-24 17:35:23,706][2364831] Updated weights for policy 0, policy_version 2608 (0.0010) | |
| [2023-02-24 17:35:24,640][2364831] Updated weights for policy 0, policy_version 2618 (0.0014) | |
| [2023-02-24 17:35:25,686][2364831] Updated weights for policy 0, policy_version 2628 (0.0014) | |
| [2023-02-24 17:35:26,266][2364708] Fps is (10 sec: 41369.5, 60 sec: 41233.2, 300 sec: 41108.9). Total num frames: 10788864. Throughput: 0: 10318.8. Samples: 1693842. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0) | |
| [2023-02-24 17:35:26,266][2364708] Avg episode reward: [(0, '32.770')] | |
| [2023-02-24 17:35:26,267][2364791] Saving new best policy, reward=32.770! | |
| [2023-02-24 17:35:26,645][2364831] Updated weights for policy 0, policy_version 2638 (0.0019) | |
| [2023-02-24 17:35:27,596][2364831] Updated weights for policy 0, policy_version 2648 (0.0012) | |
| [2023-02-24 17:35:28,675][2364831] Updated weights for policy 0, policy_version 2658 (0.0012) | |
| [2023-02-24 17:35:29,615][2364831] Updated weights for policy 0, policy_version 2668 (0.0009) | |
| [2023-02-24 17:35:30,625][2364831] Updated weights for policy 0, policy_version 2678 (0.0012) | |
| [2023-02-24 17:35:31,266][2364708] Fps is (10 sec: 41369.4, 60 sec: 41233.0, 300 sec: 41104.5). Total num frames: 10993664. Throughput: 0: 10317.5. Samples: 1724652. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2023-02-24 17:35:31,266][2364708] Avg episode reward: [(0, '33.019')] | |
| [2023-02-24 17:35:31,271][2364791] Saving new best policy, reward=33.019! | |
| [2023-02-24 17:35:31,627][2364831] Updated weights for policy 0, policy_version 2688 (0.0013) | |
| [2023-02-24 17:35:32,607][2364831] Updated weights for policy 0, policy_version 2698 (0.0012) | |
| [2023-02-24 17:35:33,625][2364831] Updated weights for policy 0, policy_version 2708 (0.0009) | |
| [2023-02-24 17:35:34,595][2364831] Updated weights for policy 0, policy_version 2718 (0.0010) | |
| [2023-02-24 17:35:35,612][2364831] Updated weights for policy 0, policy_version 2728 (0.0010) | |
| [2023-02-24 17:35:36,266][2364708] Fps is (10 sec: 40959.8, 60 sec: 41233.1, 300 sec: 41100.4). Total num frames: 11198464. Throughput: 0: 10313.8. Samples: 1786287. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0) | |
| [2023-02-24 17:35:36,266][2364708] Avg episode reward: [(0, '30.687')] | |
| [2023-02-24 17:35:36,597][2364831] Updated weights for policy 0, policy_version 2738 (0.0012) | |
| [2023-02-24 17:35:37,588][2364831] Updated weights for policy 0, policy_version 2748 (0.0012) | |
| [2023-02-24 17:35:38,625][2364831] Updated weights for policy 0, policy_version 2758 (0.0016) | |
| [2023-02-24 17:35:39,609][2364831] Updated weights for policy 0, policy_version 2768 (0.0009) | |
| [2023-02-24 17:35:40,592][2364831] Updated weights for policy 0, policy_version 2778 (0.0009) | |
| [2023-02-24 17:35:41,266][2364708] Fps is (10 sec: 40960.2, 60 sec: 41233.0, 300 sec: 41096.5). Total num frames: 11403264. Throughput: 0: 10304.3. Samples: 1847913. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2023-02-24 17:35:41,266][2364708] Avg episode reward: [(0, '30.382')] | |
| [2023-02-24 17:35:41,573][2364831] Updated weights for policy 0, policy_version 2788 (0.0012) | |
| [2023-02-24 17:35:42,590][2364831] Updated weights for policy 0, policy_version 2798 (0.0010) | |
| [2023-02-24 17:35:43,575][2364831] Updated weights for policy 0, policy_version 2808 (0.0010) | |
| [2023-02-24 17:35:44,572][2364831] Updated weights for policy 0, policy_version 2818 (0.0011) | |
| [2023-02-24 17:35:45,597][2364831] Updated weights for policy 0, policy_version 2828 (0.0008) | |
| [2023-02-24 17:35:46,266][2364708] Fps is (10 sec: 41369.3, 60 sec: 41233.1, 300 sec: 41115.0). Total num frames: 11612160. Throughput: 0: 10300.4. Samples: 1878723. Policy #0 lag: (min: 0.0, avg: 2.2, max: 4.0) | |
| [2023-02-24 17:35:46,266][2364708] Avg episode reward: [(0, '30.394')] | |
| [2023-02-24 17:35:46,560][2364831] Updated weights for policy 0, policy_version 2838 (0.0010) | |
| [2023-02-24 17:35:47,531][2364831] Updated weights for policy 0, policy_version 2848 (0.0010) | |
| [2023-02-24 17:35:48,545][2364831] Updated weights for policy 0, policy_version 2858 (0.0012) | |
| [2023-02-24 17:35:49,500][2364831] Updated weights for policy 0, policy_version 2868 (0.0010) | |
| [2023-02-24 17:35:50,524][2364831] Updated weights for policy 0, policy_version 2878 (0.0012) | |
| [2023-02-24 17:35:51,266][2364708] Fps is (10 sec: 41369.7, 60 sec: 41233.0, 300 sec: 41110.9). Total num frames: 11816960. Throughput: 0: 10303.3. Samples: 1940775. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2023-02-24 17:35:51,266][2364708] Avg episode reward: [(0, '27.697')] | |
| [2023-02-24 17:35:51,481][2364831] Updated weights for policy 0, policy_version 2888 (0.0011) | |
| [2023-02-24 17:35:52,493][2364831] Updated weights for policy 0, policy_version 2898 (0.0012) | |
| [2023-02-24 17:35:53,490][2364831] Updated weights for policy 0, policy_version 2908 (0.0009) | |
| [2023-02-24 17:35:54,455][2364831] Updated weights for policy 0, policy_version 2918 (0.0012) | |
| [2023-02-24 17:35:55,469][2364831] Updated weights for policy 0, policy_version 2928 (0.0012) | |
| [2023-02-24 17:35:56,266][2364708] Fps is (10 sec: 40960.4, 60 sec: 41233.1, 300 sec: 41107.0). Total num frames: 12021760. Throughput: 0: 10309.2. Samples: 2002731. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2023-02-24 17:35:56,266][2364708] Avg episode reward: [(0, '32.058')] | |
| [2023-02-24 17:35:56,472][2364831] Updated weights for policy 0, policy_version 2938 (0.0009) | |
| [2023-02-24 17:35:57,467][2364831] Updated weights for policy 0, policy_version 2948 (0.0011) | |
| [2023-02-24 17:35:58,438][2364831] Updated weights for policy 0, policy_version 2958 (0.0013) | |
| [2023-02-24 17:35:59,455][2364831] Updated weights for policy 0, policy_version 2968 (0.0009) | |
| [2023-02-24 17:36:00,457][2364831] Updated weights for policy 0, policy_version 2978 (0.0009) | |
| [2023-02-24 17:36:01,266][2364708] Fps is (10 sec: 41369.4, 60 sec: 41233.0, 300 sec: 41123.8). Total num frames: 12230656. Throughput: 0: 10305.4. Samples: 2033598. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2023-02-24 17:36:01,266][2364708] Avg episode reward: [(0, '29.736')] | |
| [2023-02-24 17:36:01,465][2364831] Updated weights for policy 0, policy_version 2988 (0.0009) | |
| [2023-02-24 17:36:02,473][2364831] Updated weights for policy 0, policy_version 2998 (0.0009) | |
| [2023-02-24 17:36:03,476][2364831] Updated weights for policy 0, policy_version 3008 (0.0010) | |
| [2023-02-24 17:36:04,459][2364831] Updated weights for policy 0, policy_version 3018 (0.0009) | |
| [2023-02-24 17:36:05,480][2364831] Updated weights for policy 0, policy_version 3028 (0.0011) | |
| [2023-02-24 17:36:06,266][2364708] Fps is (10 sec: 41369.1, 60 sec: 41233.0, 300 sec: 41119.8). Total num frames: 12435456. Throughput: 0: 10293.7. Samples: 2095044. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0) | |
| [2023-02-24 17:36:06,266][2364708] Avg episode reward: [(0, '30.393')] | |
| [2023-02-24 17:36:06,445][2364831] Updated weights for policy 0, policy_version 3038 (0.0012) | |
| [2023-02-24 17:36:07,421][2364831] Updated weights for policy 0, policy_version 3048 (0.0009) | |
| [2023-02-24 17:36:08,415][2364831] Updated weights for policy 0, policy_version 3058 (0.0011) | |
| [2023-02-24 17:36:09,436][2364831] Updated weights for policy 0, policy_version 3068 (0.0010) | |
| [2023-02-24 17:36:10,457][2364831] Updated weights for policy 0, policy_version 3078 (0.0009) | |
| [2023-02-24 17:36:11,266][2364708] Fps is (10 sec: 40960.7, 60 sec: 41233.3, 300 sec: 41116.0). Total num frames: 12640256. Throughput: 0: 10281.7. Samples: 2156517. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2023-02-24 17:36:11,266][2364708] Avg episode reward: [(0, '30.391')] | |
| [2023-02-24 17:36:11,465][2364831] Updated weights for policy 0, policy_version 3088 (0.0009) | |
| [2023-02-24 17:36:12,457][2364831] Updated weights for policy 0, policy_version 3098 (0.0011) | |
| [2023-02-24 17:36:13,406][2364831] Updated weights for policy 0, policy_version 3108 (0.0013) | |
| [2023-02-24 17:36:14,404][2364831] Updated weights for policy 0, policy_version 3118 (0.0012) | |
| [2023-02-24 17:36:15,425][2364831] Updated weights for policy 0, policy_version 3128 (0.0011) | |
| [2023-02-24 17:36:16,266][2364708] Fps is (10 sec: 40960.3, 60 sec: 41164.7, 300 sec: 41112.4). Total num frames: 12845056. Throughput: 0: 10287.8. Samples: 2187600. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2023-02-24 17:36:16,266][2364708] Avg episode reward: [(0, '27.913')] | |
| [2023-02-24 17:36:16,372][2364831] Updated weights for policy 0, policy_version 3138 (0.0014) | |
| [2023-02-24 17:36:17,447][2364831] Updated weights for policy 0, policy_version 3148 (0.0009) | |
| [2023-02-24 17:36:18,429][2364831] Updated weights for policy 0, policy_version 3158 (0.0009) | |
| [2023-02-24 17:36:19,407][2364831] Updated weights for policy 0, policy_version 3168 (0.0013) | |
| [2023-02-24 17:36:20,357][2364831] Updated weights for policy 0, policy_version 3178 (0.0009) | |
| [2023-02-24 17:36:21,266][2364708] Fps is (10 sec: 40959.6, 60 sec: 41164.8, 300 sec: 41108.9). Total num frames: 13049856. Throughput: 0: 10288.8. Samples: 2249286. Policy #0 lag: (min: 0.0, avg: 1.9, max: 3.0) | |
| [2023-02-24 17:36:21,266][2364708] Avg episode reward: [(0, '32.921')] | |
| [2023-02-24 17:36:21,375][2364831] Updated weights for policy 0, policy_version 3188 (0.0012) | |
| [2023-02-24 17:36:22,374][2364831] Updated weights for policy 0, policy_version 3198 (0.0015) | |
| [2023-02-24 17:36:23,132][2364791] Signal inference workers to stop experience collection... (50 times) | |
| [2023-02-24 17:36:23,134][2364791] Signal inference workers to resume experience collection... (50 times) | |
| [2023-02-24 17:36:23,142][2364831] InferenceWorker_p0-w0: stopping experience collection (50 times) | |
| [2023-02-24 17:36:23,145][2364831] InferenceWorker_p0-w0: resuming experience collection (50 times) | |
| [2023-02-24 17:36:23,415][2364831] Updated weights for policy 0, policy_version 3208 (0.0010) | |
| [2023-02-24 17:36:24,357][2364831] Updated weights for policy 0, policy_version 3218 (0.0009) | |
| [2023-02-24 17:36:25,363][2364831] Updated weights for policy 0, policy_version 3228 (0.0014) | |
| [2023-02-24 17:36:26,266][2364708] Fps is (10 sec: 41369.4, 60 sec: 41164.7, 300 sec: 41123.8). Total num frames: 13258752. Throughput: 0: 10290.0. Samples: 2310963. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2023-02-24 17:36:26,266][2364708] Avg episode reward: [(0, '34.018')] | |
| [2023-02-24 17:36:26,267][2364791] Saving new best policy, reward=34.018! | |
| [2023-02-24 17:36:26,376][2364831] Updated weights for policy 0, policy_version 3238 (0.0009) | |
| [2023-02-24 17:36:27,385][2364831] Updated weights for policy 0, policy_version 3248 (0.0012) | |
| [2023-02-24 17:36:28,374][2364831] Updated weights for policy 0, policy_version 3258 (0.0008) | |
| [2023-02-24 17:36:29,381][2364831] Updated weights for policy 0, policy_version 3268 (0.0009) | |
| [2023-02-24 17:36:30,372][2364831] Updated weights for policy 0, policy_version 3278 (0.0009) | |
| [2023-02-24 17:36:31,266][2364708] Fps is (10 sec: 41369.5, 60 sec: 41164.8, 300 sec: 41120.3). Total num frames: 13463552. Throughput: 0: 10287.8. Samples: 2341674. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2023-02-24 17:36:31,266][2364708] Avg episode reward: [(0, '31.155')] | |
| [2023-02-24 17:36:31,271][2364791] Saving /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000003287_13463552.pth... | |
| [2023-02-24 17:36:31,331][2364791] Removing /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth | |
| [2023-02-24 17:36:31,376][2364831] Updated weights for policy 0, policy_version 3288 (0.0010) | |
| [2023-02-24 17:36:32,389][2364831] Updated weights for policy 0, policy_version 3298 (0.0012) | |
| [2023-02-24 17:36:33,398][2364831] Updated weights for policy 0, policy_version 3308 (0.0013) | |
| [2023-02-24 17:36:34,328][2364831] Updated weights for policy 0, policy_version 3318 (0.0009) | |
| [2023-02-24 17:36:35,370][2364831] Updated weights for policy 0, policy_version 3328 (0.0009) | |
| [2023-02-24 17:36:36,266][2364708] Fps is (10 sec: 40960.6, 60 sec: 41164.8, 300 sec: 41116.9). Total num frames: 13668352. Throughput: 0: 10277.8. Samples: 2403273. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2023-02-24 17:36:36,266][2364708] Avg episode reward: [(0, '32.249')] | |
| [2023-02-24 17:36:36,352][2364831] Updated weights for policy 0, policy_version 3338 (0.0008) | |
| [2023-02-24 17:36:37,358][2364831] Updated weights for policy 0, policy_version 3348 (0.0012) | |
| [2023-02-24 17:36:38,366][2364831] Updated weights for policy 0, policy_version 3358 (0.0013) | |
| [2023-02-24 17:36:39,348][2364831] Updated weights for policy 0, policy_version 3368 (0.0010) | |
| [2023-02-24 17:36:40,325][2364831] Updated weights for policy 0, policy_version 3378 (0.0009) | |
| [2023-02-24 17:36:41,266][2364708] Fps is (10 sec: 40960.6, 60 sec: 41164.9, 300 sec: 41113.6). Total num frames: 13873152. Throughput: 0: 10271.1. Samples: 2464929. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2023-02-24 17:36:41,266][2364708] Avg episode reward: [(0, '30.922')] | |
| [2023-02-24 17:36:41,354][2364831] Updated weights for policy 0, policy_version 3388 (0.0013) | |
| [2023-02-24 17:36:42,336][2364831] Updated weights for policy 0, policy_version 3398 (0.0011) | |
| [2023-02-24 17:36:43,307][2364831] Updated weights for policy 0, policy_version 3408 (0.0010) | |
| [2023-02-24 17:36:44,352][2364831] Updated weights for policy 0, policy_version 3418 (0.0017) | |
| [2023-02-24 17:36:45,308][2364831] Updated weights for policy 0, policy_version 3428 (0.0011) | |
| [2023-02-24 17:36:46,266][2364708] Fps is (10 sec: 40959.9, 60 sec: 41096.6, 300 sec: 41110.5). Total num frames: 14077952. Throughput: 0: 10271.3. Samples: 2495805. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2023-02-24 17:36:46,266][2364708] Avg episode reward: [(0, '35.645')] | |
| [2023-02-24 17:36:46,267][2364791] Saving new best policy, reward=35.645! | |
| [2023-02-24 17:36:46,360][2364831] Updated weights for policy 0, policy_version 3438 (0.0011) | |
| [2023-02-24 17:36:47,341][2364831] Updated weights for policy 0, policy_version 3448 (0.0010) | |
| [2023-02-24 17:36:48,315][2364831] Updated weights for policy 0, policy_version 3458 (0.0012) | |
| [2023-02-24 17:36:49,289][2364831] Updated weights for policy 0, policy_version 3468 (0.0008) | |
| [2023-02-24 17:36:50,307][2364831] Updated weights for policy 0, policy_version 3478 (0.0009) | |
| [2023-02-24 17:36:51,266][2364708] Fps is (10 sec: 40959.9, 60 sec: 41096.6, 300 sec: 41107.5). Total num frames: 14282752. Throughput: 0: 10276.8. Samples: 2557500. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0) | |
| [2023-02-24 17:36:51,266][2364708] Avg episode reward: [(0, '34.180')] | |
| [2023-02-24 17:36:51,296][2364831] Updated weights for policy 0, policy_version 3488 (0.0009) | |
| [2023-02-24 17:36:52,295][2364831] Updated weights for policy 0, policy_version 3498 (0.0014) | |
| [2023-02-24 17:36:53,320][2364831] Updated weights for policy 0, policy_version 3508 (0.0010) | |
| [2023-02-24 17:36:54,312][2364831] Updated weights for policy 0, policy_version 3518 (0.0013) | |
| [2023-02-24 17:36:55,310][2364831] Updated weights for policy 0, policy_version 3528 (0.0012) | |
| [2023-02-24 17:36:56,260][2364831] Updated weights for policy 0, policy_version 3538 (0.0011) | |
| [2023-02-24 17:36:56,266][2364708] Fps is (10 sec: 41369.7, 60 sec: 41164.9, 300 sec: 41120.6). Total num frames: 14491648. Throughput: 0: 10279.0. Samples: 2619072. Policy #0 lag: (min: 0.0, avg: 2.0, max: 5.0) | |
| [2023-02-24 17:36:56,266][2364708] Avg episode reward: [(0, '35.711')] | |
| [2023-02-24 17:36:56,267][2364791] Saving new best policy, reward=35.711! | |
| [2023-02-24 17:36:57,297][2364831] Updated weights for policy 0, policy_version 3548 (0.0014) | |
| [2023-02-24 17:36:58,305][2364831] Updated weights for policy 0, policy_version 3558 (0.0009) | |
| [2023-02-24 17:36:59,282][2364831] Updated weights for policy 0, policy_version 3568 (0.0009) | |
| [2023-02-24 17:37:00,281][2364831] Updated weights for policy 0, policy_version 3578 (0.0018) | |
| [2023-02-24 17:37:01,266][2364708] Fps is (10 sec: 40960.0, 60 sec: 41028.4, 300 sec: 41101.8). Total num frames: 14692352. Throughput: 0: 10270.1. Samples: 2649753. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2023-02-24 17:37:01,266][2364708] Avg episode reward: [(0, '32.713')] | |
| [2023-02-24 17:37:01,290][2364831] Updated weights for policy 0, policy_version 3588 (0.0011) | |
| [2023-02-24 17:37:02,293][2364831] Updated weights for policy 0, policy_version 3598 (0.0012) | |
| [2023-02-24 17:37:03,300][2364831] Updated weights for policy 0, policy_version 3608 (0.0010) | |
| [2023-02-24 17:37:04,288][2364831] Updated weights for policy 0, policy_version 3618 (0.0012) | |
| [2023-02-24 17:37:05,307][2364831] Updated weights for policy 0, policy_version 3628 (0.0012) | |
| [2023-02-24 17:37:06,256][2364831] Updated weights for policy 0, policy_version 3638 (0.0011) | |
| [2023-02-24 17:37:06,266][2364708] Fps is (10 sec: 40959.4, 60 sec: 41096.6, 300 sec: 41114.5). Total num frames: 14901248. Throughput: 0: 10265.3. Samples: 2711226. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2023-02-24 17:37:06,266][2364708] Avg episode reward: [(0, '33.770')] | |
| [2023-02-24 17:37:07,256][2364831] Updated weights for policy 0, policy_version 3648 (0.0010) | |
| [2023-02-24 17:37:08,283][2364831] Updated weights for policy 0, policy_version 3658 (0.0010) | |
| [2023-02-24 17:37:09,271][2364831] Updated weights for policy 0, policy_version 3668 (0.0010) | |
| [2023-02-24 17:37:10,247][2364831] Updated weights for policy 0, policy_version 3678 (0.0011) | |
| [2023-02-24 17:37:11,255][2364831] Updated weights for policy 0, policy_version 3688 (0.0009) | |
| [2023-02-24 17:37:11,266][2364708] Fps is (10 sec: 41369.7, 60 sec: 41096.5, 300 sec: 41111.7). Total num frames: 15106048. Throughput: 0: 10267.2. Samples: 2772984. Policy #0 lag: (min: 0.0, avg: 2.1, max: 5.0) | |
| [2023-02-24 17:37:11,266][2364708] Avg episode reward: [(0, '35.557')] | |
| [2023-02-24 17:37:12,240][2364831] Updated weights for policy 0, policy_version 3698 (0.0010) | |
| [2023-02-24 17:37:13,251][2364831] Updated weights for policy 0, policy_version 3708 (0.0010) | |
| [2023-02-24 17:37:14,229][2364831] Updated weights for policy 0, policy_version 3718 (0.0009) | |
| [2023-02-24 17:37:15,279][2364831] Updated weights for policy 0, policy_version 3728 (0.0015) | |
| [2023-02-24 17:37:16,243][2364831] Updated weights for policy 0, policy_version 3738 (0.0011) | |
| [2023-02-24 17:37:16,266][2364708] Fps is (10 sec: 40960.5, 60 sec: 41096.6, 300 sec: 41108.9). Total num frames: 15310848. Throughput: 0: 10269.1. Samples: 2803782. Policy #0 lag: (min: 0.0, avg: 2.2, max: 4.0) | |
| [2023-02-24 17:37:16,266][2364708] Avg episode reward: [(0, '34.978')] | |
| [2023-02-24 17:37:17,232][2364831] Updated weights for policy 0, policy_version 3748 (0.0011) | |
| [2023-02-24 17:37:18,232][2364831] Updated weights for policy 0, policy_version 3758 (0.0012) | |
| [2023-02-24 17:37:19,246][2364831] Updated weights for policy 0, policy_version 3768 (0.0011) | |
| [2023-02-24 17:37:20,215][2364831] Updated weights for policy 0, policy_version 3778 (0.0016) | |
| [2023-02-24 17:37:21,224][2364831] Updated weights for policy 0, policy_version 3788 (0.0009) | |
| [2023-02-24 17:37:21,266][2364708] Fps is (10 sec: 40959.6, 60 sec: 41096.5, 300 sec: 41106.3). Total num frames: 15515648. Throughput: 0: 10267.2. Samples: 2865300. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2023-02-24 17:37:21,266][2364708] Avg episode reward: [(0, '32.422')] | |
| [2023-02-24 17:37:22,190][2364831] Updated weights for policy 0, policy_version 3798 (0.0009) | |
| [2023-02-24 17:37:23,210][2364831] Updated weights for policy 0, policy_version 3808 (0.0010) | |
| [2023-02-24 17:37:24,201][2364831] Updated weights for policy 0, policy_version 3818 (0.0009) | |
| [2023-02-24 17:37:25,224][2364831] Updated weights for policy 0, policy_version 3828 (0.0012) | |
| [2023-02-24 17:37:26,251][2364831] Updated weights for policy 0, policy_version 3838 (0.0012) | |
| [2023-02-24 17:37:26,266][2364708] Fps is (10 sec: 40960.0, 60 sec: 41028.4, 300 sec: 41103.7). Total num frames: 15720448. Throughput: 0: 10264.2. Samples: 2926818. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2023-02-24 17:37:26,266][2364708] Avg episode reward: [(0, '30.861')] | |
| [2023-02-24 17:37:27,226][2364831] Updated weights for policy 0, policy_version 3848 (0.0014) | |
| [2023-02-24 17:37:28,214][2364831] Updated weights for policy 0, policy_version 3858 (0.0010) | |
| [2023-02-24 17:37:29,243][2364831] Updated weights for policy 0, policy_version 3868 (0.0013) | |
| [2023-02-24 17:37:30,235][2364831] Updated weights for policy 0, policy_version 3878 (0.0009) | |
| [2023-02-24 17:37:31,194][2364831] Updated weights for policy 0, policy_version 3888 (0.0010) | |
| [2023-02-24 17:37:31,266][2364708] Fps is (10 sec: 40959.8, 60 sec: 41028.3, 300 sec: 41101.2). Total num frames: 15925248. Throughput: 0: 10260.7. Samples: 2957538. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2023-02-24 17:37:31,266][2364708] Avg episode reward: [(0, '33.478')] | |
| [2023-02-24 17:37:32,210][2364831] Updated weights for policy 0, policy_version 3898 (0.0011) | |
| [2023-02-24 17:37:33,187][2364831] Updated weights for policy 0, policy_version 3908 (0.0013) | |
| [2023-02-24 17:37:34,160][2364831] Updated weights for policy 0, policy_version 3918 (0.0012) | |
| [2023-02-24 17:37:35,197][2364831] Updated weights for policy 0, policy_version 3928 (0.0012) | |
| [2023-02-24 17:37:36,189][2364831] Updated weights for policy 0, policy_version 3938 (0.0012) | |
| [2023-02-24 17:37:36,266][2364708] Fps is (10 sec: 40960.0, 60 sec: 41028.3, 300 sec: 41098.8). Total num frames: 16130048. Throughput: 0: 10267.2. Samples: 3019524. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0) | |
| [2023-02-24 17:37:36,266][2364708] Avg episode reward: [(0, '34.030')] | |
| [2023-02-24 17:37:37,168][2364831] Updated weights for policy 0, policy_version 3948 (0.0010) | |
| [2023-02-24 17:37:38,212][2364831] Updated weights for policy 0, policy_version 3958 (0.0010) | |
| [2023-02-24 17:37:39,181][2364831] Updated weights for policy 0, policy_version 3968 (0.0009) | |
| [2023-02-24 17:37:40,158][2364831] Updated weights for policy 0, policy_version 3978 (0.0012) | |
| [2023-02-24 17:37:41,178][2364831] Updated weights for policy 0, policy_version 3988 (0.0011) | |
| [2023-02-24 17:37:41,266][2364708] Fps is (10 sec: 40960.6, 60 sec: 41028.3, 300 sec: 41223.8). Total num frames: 16334848. Throughput: 0: 10262.3. Samples: 3080874. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2023-02-24 17:37:41,266][2364708] Avg episode reward: [(0, '30.119')] | |
| [2023-02-24 17:37:42,173][2364831] Updated weights for policy 0, policy_version 3998 (0.0009) | |
| [2023-02-24 17:37:43,173][2364831] Updated weights for policy 0, policy_version 4008 (0.0012) | |
| [2023-02-24 17:37:44,204][2364831] Updated weights for policy 0, policy_version 4018 (0.0013) | |
| [2023-02-24 17:37:45,182][2364831] Updated weights for policy 0, policy_version 4028 (0.0015) | |
| [2023-02-24 17:37:46,192][2364831] Updated weights for policy 0, policy_version 4038 (0.0010) | |
| [2023-02-24 17:37:46,266][2364708] Fps is (10 sec: 40959.9, 60 sec: 41028.2, 300 sec: 41209.9). Total num frames: 16539648. Throughput: 0: 10264.2. Samples: 3111642. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2023-02-24 17:37:46,266][2364708] Avg episode reward: [(0, '34.674')] | |
| [2023-02-24 17:37:47,165][2364831] Updated weights for policy 0, policy_version 4048 (0.0009) | |
| [2023-02-24 17:37:48,150][2364831] Updated weights for policy 0, policy_version 4058 (0.0009) | |
| [2023-02-24 17:37:49,155][2364831] Updated weights for policy 0, policy_version 4068 (0.0010) | |
| [2023-02-24 17:37:50,176][2364831] Updated weights for policy 0, policy_version 4078 (0.0011) | |
| [2023-02-24 17:37:51,128][2364831] Updated weights for policy 0, policy_version 4088 (0.0013) | |
| [2023-02-24 17:37:51,266][2364708] Fps is (10 sec: 41369.0, 60 sec: 41096.4, 300 sec: 41209.9). Total num frames: 16748544. Throughput: 0: 10268.4. Samples: 3173304. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2023-02-24 17:37:51,267][2364708] Avg episode reward: [(0, '33.236')] | |
| [2023-02-24 17:37:52,111][2364831] Updated weights for policy 0, policy_version 4098 (0.0009) | |
| [2023-02-24 17:37:53,146][2364831] Updated weights for policy 0, policy_version 4108 (0.0014) | |
| [2023-02-24 17:37:54,142][2364831] Updated weights for policy 0, policy_version 4118 (0.0012) | |
| [2023-02-24 17:37:55,117][2364831] Updated weights for policy 0, policy_version 4128 (0.0010) | |
| [2023-02-24 17:37:56,172][2364831] Updated weights for policy 0, policy_version 4138 (0.0011) | |
| [2023-02-24 17:37:56,266][2364708] Fps is (10 sec: 41369.4, 60 sec: 41028.2, 300 sec: 41209.9). Total num frames: 16953344. Throughput: 0: 10265.4. Samples: 3234927. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0) | |
| [2023-02-24 17:37:56,266][2364708] Avg episode reward: [(0, '33.288')] | |
| [2023-02-24 17:37:57,176][2364831] Updated weights for policy 0, policy_version 4148 (0.0009) | |
| [2023-02-24 17:37:58,108][2364831] Updated weights for policy 0, policy_version 4158 (0.0010) | |
| [2023-02-24 17:37:59,170][2364831] Updated weights for policy 0, policy_version 4168 (0.0016) | |
| [2023-02-24 17:38:00,167][2364831] Updated weights for policy 0, policy_version 4178 (0.0016) | |
| [2023-02-24 17:38:01,108][2364831] Updated weights for policy 0, policy_version 4188 (0.0011) | |
| [2023-02-24 17:38:01,266][2364708] Fps is (10 sec: 40550.7, 60 sec: 41028.2, 300 sec: 41182.2). Total num frames: 17154048. Throughput: 0: 10261.8. Samples: 3265563. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0) | |
| [2023-02-24 17:38:01,266][2364708] Avg episode reward: [(0, '35.841')] | |
| [2023-02-24 17:38:01,270][2364791] Saving new best policy, reward=35.841! | |
| [2023-02-24 17:38:02,155][2364831] Updated weights for policy 0, policy_version 4198 (0.0012) | |
| [2023-02-24 17:38:03,132][2364831] Updated weights for policy 0, policy_version 4208 (0.0009) | |
| [2023-02-24 17:38:04,177][2364831] Updated weights for policy 0, policy_version 4218 (0.0012) | |
| [2023-02-24 17:38:05,155][2364831] Updated weights for policy 0, policy_version 4228 (0.0013) | |
| [2023-02-24 17:38:06,137][2364831] Updated weights for policy 0, policy_version 4238 (0.0010) | |
| [2023-02-24 17:38:06,266][2364708] Fps is (10 sec: 40960.0, 60 sec: 41028.3, 300 sec: 41182.2). Total num frames: 17362944. Throughput: 0: 10260.6. Samples: 3327027. Policy #0 lag: (min: 1.0, avg: 2.0, max: 4.0) | |
| [2023-02-24 17:38:06,266][2364708] Avg episode reward: [(0, '34.701')] | |
| [2023-02-24 17:38:07,128][2364831] Updated weights for policy 0, policy_version 4248 (0.0010) | |
| [2023-02-24 17:38:08,120][2364831] Updated weights for policy 0, policy_version 4258 (0.0009) | |
| [2023-02-24 17:38:09,120][2364831] Updated weights for policy 0, policy_version 4268 (0.0010) | |
| [2023-02-24 17:38:10,112][2364831] Updated weights for policy 0, policy_version 4278 (0.0009) | |
| [2023-02-24 17:38:11,084][2364831] Updated weights for policy 0, policy_version 4288 (0.0009) | |
| [2023-02-24 17:38:11,266][2364708] Fps is (10 sec: 41368.9, 60 sec: 41028.1, 300 sec: 41182.1). Total num frames: 17567744. Throughput: 0: 10268.7. Samples: 3388911. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2023-02-24 17:38:11,267][2364708] Avg episode reward: [(0, '32.559')] | |
| [2023-02-24 17:38:12,108][2364831] Updated weights for policy 0, policy_version 4298 (0.0009) | |
| [2023-02-24 17:38:13,088][2364831] Updated weights for policy 0, policy_version 4308 (0.0011) | |
| [2023-02-24 17:38:14,094][2364831] Updated weights for policy 0, policy_version 4318 (0.0009) | |
| [2023-02-24 17:38:15,081][2364831] Updated weights for policy 0, policy_version 4328 (0.0009) | |
| [2023-02-24 17:38:16,054][2364831] Updated weights for policy 0, policy_version 4338 (0.0010) | |
| [2023-02-24 17:38:16,266][2364708] Fps is (10 sec: 40959.2, 60 sec: 41028.1, 300 sec: 41168.2). Total num frames: 17772544. Throughput: 0: 10274.2. Samples: 3419880. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2023-02-24 17:38:16,267][2364708] Avg episode reward: [(0, '32.783')] | |
| [2023-02-24 17:38:17,103][2364831] Updated weights for policy 0, policy_version 4348 (0.0012) | |
| [2023-02-24 17:38:18,095][2364831] Updated weights for policy 0, policy_version 4358 (0.0009) | |
| [2023-02-24 17:38:19,078][2364831] Updated weights for policy 0, policy_version 4368 (0.0011) | |
| [2023-02-24 17:38:20,078][2364831] Updated weights for policy 0, policy_version 4378 (0.0012) | |
| [2023-02-24 17:38:21,065][2364831] Updated weights for policy 0, policy_version 4388 (0.0016) | |
| [2023-02-24 17:38:21,266][2364708] Fps is (10 sec: 41370.7, 60 sec: 41096.6, 300 sec: 41182.2). Total num frames: 17981440. Throughput: 0: 10262.9. Samples: 3481353. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2023-02-24 17:38:21,266][2364708] Avg episode reward: [(0, '35.299')] | |
| [2023-02-24 17:38:22,058][2364831] Updated weights for policy 0, policy_version 4398 (0.0012) | |
| [2023-02-24 17:38:23,045][2364831] Updated weights for policy 0, policy_version 4408 (0.0010) | |
| [2023-02-24 17:38:24,107][2364831] Updated weights for policy 0, policy_version 4418 (0.0011) | |
| [2023-02-24 17:38:25,058][2364831] Updated weights for policy 0, policy_version 4428 (0.0009) | |
| [2023-02-24 17:38:26,042][2364831] Updated weights for policy 0, policy_version 4438 (0.0012) | |
| [2023-02-24 17:38:26,266][2364708] Fps is (10 sec: 40960.7, 60 sec: 41028.2, 300 sec: 41154.4). Total num frames: 18182144. Throughput: 0: 10268.6. Samples: 3542961. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2023-02-24 17:38:26,266][2364708] Avg episode reward: [(0, '33.602')] | |
| [2023-02-24 17:38:27,045][2364831] Updated weights for policy 0, policy_version 4448 (0.0013) | |
| [2023-02-24 17:38:28,079][2364831] Updated weights for policy 0, policy_version 4458 (0.0009) | |
| [2023-02-24 17:38:29,077][2364831] Updated weights for policy 0, policy_version 4468 (0.0012) | |
| [2023-02-24 17:38:30,014][2364831] Updated weights for policy 0, policy_version 4478 (0.0014) | |
| [2023-02-24 17:38:31,056][2364831] Updated weights for policy 0, policy_version 4488 (0.0014) | |
| [2023-02-24 17:38:31,266][2364708] Fps is (10 sec: 40959.3, 60 sec: 41096.5, 300 sec: 41168.3). Total num frames: 18391040. Throughput: 0: 10269.4. Samples: 3573768. Policy #0 lag: (min: 0.0, avg: 2.0, max: 5.0) | |
| [2023-02-24 17:38:31,266][2364708] Avg episode reward: [(0, '30.251')] | |
| [2023-02-24 17:38:31,271][2364791] Saving /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000004490_18391040.pth... | |
| [2023-02-24 17:38:31,336][2364791] Removing /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000002080_8519680.pth | |
| [2023-02-24 17:38:32,050][2364831] Updated weights for policy 0, policy_version 4498 (0.0012) | |
| [2023-02-24 17:38:33,042][2364831] Updated weights for policy 0, policy_version 4508 (0.0009) | |
| [2023-02-24 17:38:34,048][2364831] Updated weights for policy 0, policy_version 4518 (0.0010) | |
| [2023-02-24 17:38:35,020][2364831] Updated weights for policy 0, policy_version 4528 (0.0010) | |
| [2023-02-24 17:38:36,020][2364831] Updated weights for policy 0, policy_version 4538 (0.0010) | |
| [2023-02-24 17:38:36,266][2364708] Fps is (10 sec: 41369.6, 60 sec: 41096.5, 300 sec: 41140.5). Total num frames: 18595840. Throughput: 0: 10268.5. Samples: 3635388. Policy #0 lag: (min: 0.0, avg: 2.0, max: 5.0) | |
| [2023-02-24 17:38:36,266][2364708] Avg episode reward: [(0, '34.728')] | |
| [2023-02-24 17:38:37,018][2364831] Updated weights for policy 0, policy_version 4548 (0.0012) | |
| [2023-02-24 17:38:37,996][2364831] Updated weights for policy 0, policy_version 4558 (0.0009) | |
| [2023-02-24 17:38:39,029][2364831] Updated weights for policy 0, policy_version 4568 (0.0010) | |
| [2023-02-24 17:38:40,017][2364831] Updated weights for policy 0, policy_version 4578 (0.0010) | |
| [2023-02-24 17:38:40,985][2364831] Updated weights for policy 0, policy_version 4588 (0.0010) | |
| [2023-02-24 17:38:41,266][2364708] Fps is (10 sec: 40959.9, 60 sec: 41096.4, 300 sec: 41154.4). Total num frames: 18800640. Throughput: 0: 10268.8. Samples: 3697023. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2023-02-24 17:38:41,267][2364708] Avg episode reward: [(0, '32.483')] | |
| [2023-02-24 17:38:42,014][2364831] Updated weights for policy 0, policy_version 4598 (0.0014) | |
| [2023-02-24 17:38:42,975][2364831] Updated weights for policy 0, policy_version 4608 (0.0009) | |
| [2023-02-24 17:38:44,032][2364831] Updated weights for policy 0, policy_version 4618 (0.0009) | |
| [2023-02-24 17:38:45,014][2364831] Updated weights for policy 0, policy_version 4628 (0.0011) | |
| [2023-02-24 17:38:45,974][2364831] Updated weights for policy 0, policy_version 4638 (0.0012) | |
| [2023-02-24 17:38:46,266][2364708] Fps is (10 sec: 41370.5, 60 sec: 41164.9, 300 sec: 41168.3). Total num frames: 19009536. Throughput: 0: 10273.0. Samples: 3727845. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0) | |
| [2023-02-24 17:38:46,266][2364708] Avg episode reward: [(0, '34.188')] | |
| [2023-02-24 17:38:47,022][2364831] Updated weights for policy 0, policy_version 4648 (0.0014) | |
| [2023-02-24 17:38:48,027][2364831] Updated weights for policy 0, policy_version 4658 (0.0013) | |
| [2023-02-24 17:38:49,020][2364831] Updated weights for policy 0, policy_version 4668 (0.0010) | |
| [2023-02-24 17:38:50,024][2364831] Updated weights for policy 0, policy_version 4678 (0.0010) | |
| [2023-02-24 17:38:51,024][2364831] Updated weights for policy 0, policy_version 4688 (0.0011) | |
| [2023-02-24 17:38:51,266][2364708] Fps is (10 sec: 40960.4, 60 sec: 41028.3, 300 sec: 41140.5). Total num frames: 19210240. Throughput: 0: 10270.9. Samples: 3789216. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2023-02-24 17:38:51,266][2364708] Avg episode reward: [(0, '36.140')] | |
| [2023-02-24 17:38:51,270][2364791] Saving new best policy, reward=36.140! | |
| [2023-02-24 17:38:52,009][2364831] Updated weights for policy 0, policy_version 4698 (0.0012) | |
| [2023-02-24 17:38:53,006][2364831] Updated weights for policy 0, policy_version 4708 (0.0011) | |
| [2023-02-24 17:38:54,017][2364831] Updated weights for policy 0, policy_version 4718 (0.0012) | |
| [2023-02-24 17:38:54,981][2364831] Updated weights for policy 0, policy_version 4728 (0.0011) | |
| [2023-02-24 17:38:55,968][2364831] Updated weights for policy 0, policy_version 4738 (0.0012) | |
| [2023-02-24 17:38:56,266][2364708] Fps is (10 sec: 40959.4, 60 sec: 41096.6, 300 sec: 41154.4). Total num frames: 19419136. Throughput: 0: 10265.0. Samples: 3850833. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0) | |
| [2023-02-24 17:38:56,266][2364708] Avg episode reward: [(0, '32.669')] | |
| [2023-02-24 17:38:56,994][2364831] Updated weights for policy 0, policy_version 4748 (0.0011) | |
| [2023-02-24 17:38:57,985][2364831] Updated weights for policy 0, policy_version 4758 (0.0008) | |
| [2023-02-24 17:38:58,970][2364831] Updated weights for policy 0, policy_version 4768 (0.0010) | |
| [2023-02-24 17:38:59,953][2364831] Updated weights for policy 0, policy_version 4778 (0.0010) | |
| [2023-02-24 17:39:00,969][2364831] Updated weights for policy 0, policy_version 4788 (0.0012) | |
| [2023-02-24 17:39:01,266][2364708] Fps is (10 sec: 41369.3, 60 sec: 41164.8, 300 sec: 41140.5). Total num frames: 19623936. Throughput: 0: 10264.2. Samples: 3881769. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2023-02-24 17:39:01,266][2364708] Avg episode reward: [(0, '33.503')] | |
| [2023-02-24 17:39:01,956][2364831] Updated weights for policy 0, policy_version 4798 (0.0011) | |
| [2023-02-24 17:39:02,959][2364831] Updated weights for policy 0, policy_version 4808 (0.0009) | |
| [2023-02-24 17:39:03,937][2364831] Updated weights for policy 0, policy_version 4818 (0.0010) | |
| [2023-02-24 17:39:04,994][2364831] Updated weights for policy 0, policy_version 4828 (0.0012) | |
| [2023-02-24 17:39:05,948][2364831] Updated weights for policy 0, policy_version 4838 (0.0009) | |
| [2023-02-24 17:39:06,266][2364708] Fps is (10 sec: 40959.8, 60 sec: 41096.5, 300 sec: 41140.5). Total num frames: 19828736. Throughput: 0: 10266.0. Samples: 3943326. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2023-02-24 17:39:06,266][2364708] Avg episode reward: [(0, '33.048')] | |
| [2023-02-24 17:39:06,927][2364831] Updated weights for policy 0, policy_version 4848 (0.0009) | |
| [2023-02-24 17:39:07,963][2364831] Updated weights for policy 0, policy_version 4858 (0.0010) | |
| [2023-02-24 17:39:08,957][2364831] Updated weights for policy 0, policy_version 4868 (0.0013) | |
| [2023-02-24 17:39:09,952][2364831] Updated weights for policy 0, policy_version 4878 (0.0009) | |
| [2023-02-24 17:39:10,563][2364791] Stopping Batcher_0... | |
| [2023-02-24 17:39:10,563][2364708] Component Batcher_0 stopped! | |
| [2023-02-24 17:39:10,564][2364791] Loop batcher_evt_loop terminating... | |
| [2023-02-24 17:39:10,566][2364791] Saving /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000004884_20004864.pth... | |
| [2023-02-24 17:39:10,580][2365108] Stopping RolloutWorker_w15... | |
| [2023-02-24 17:39:10,580][2364708] Component RolloutWorker_w15 stopped! | |
| [2023-02-24 17:39:10,580][2364862] Stopping RolloutWorker_w14... | |
| [2023-02-24 17:39:10,581][2364708] Component RolloutWorker_w14 stopped! | |
| [2023-02-24 17:39:10,581][2364855] Stopping RolloutWorker_w10... | |
| [2023-02-24 17:39:10,581][2364708] Component RolloutWorker_w10 stopped! | |
| [2023-02-24 17:39:10,581][2364855] Loop rollout_proc10_evt_loop terminating... | |
| [2023-02-24 17:39:10,581][2364708] Component RolloutWorker_w0 stopped! | |
| [2023-02-24 17:39:10,581][2365108] Loop rollout_proc15_evt_loop terminating... | |
| [2023-02-24 17:39:10,581][2364832] Stopping RolloutWorker_w0... | |
| [2023-02-24 17:39:10,582][2364862] Loop rollout_proc14_evt_loop terminating... | |
| [2023-02-24 17:39:10,582][2364708] Component RolloutWorker_w3 stopped! | |
| [2023-02-24 17:39:10,582][2364836] Stopping RolloutWorker_w3... | |
| [2023-02-24 17:39:10,582][2364857] Stopping RolloutWorker_w11... | |
| [2023-02-24 17:39:10,582][2364832] Loop rollout_proc0_evt_loop terminating... | |
| [2023-02-24 17:39:10,583][2364708] Component RolloutWorker_w11 stopped! | |
| [2023-02-24 17:39:10,583][2364836] Loop rollout_proc3_evt_loop terminating... | |
| [2023-02-24 17:39:10,583][2364859] Stopping RolloutWorker_w8... | |
| [2023-02-24 17:39:10,583][2364857] Loop rollout_proc11_evt_loop terminating... | |
| [2023-02-24 17:39:10,583][2364708] Component RolloutWorker_w8 stopped! | |
| [2023-02-24 17:39:10,583][2364861] Stopping RolloutWorker_w13... | |
| [2023-02-24 17:39:10,583][2364833] Stopping RolloutWorker_w1... | |
| [2023-02-24 17:39:10,583][2364839] Stopping RolloutWorker_w7... | |
| [2023-02-24 17:39:10,583][2364838] Stopping RolloutWorker_w6... | |
| [2023-02-24 17:39:10,583][2364708] Component RolloutWorker_w13 stopped! | |
| [2023-02-24 17:39:10,583][2364861] Loop rollout_proc13_evt_loop terminating... | |
| [2023-02-24 17:39:10,583][2364708] Component RolloutWorker_w1 stopped! | |
| [2023-02-24 17:39:10,583][2364833] Loop rollout_proc1_evt_loop terminating... | |
| [2023-02-24 17:39:10,583][2364838] Loop rollout_proc6_evt_loop terminating... | |
| [2023-02-24 17:39:10,583][2364839] Loop rollout_proc7_evt_loop terminating... | |
| [2023-02-24 17:39:10,583][2364860] Stopping RolloutWorker_w12... | |
| [2023-02-24 17:39:10,583][2364708] Component RolloutWorker_w7 stopped! | |
| [2023-02-24 17:39:10,584][2364708] Component RolloutWorker_w6 stopped! | |
| [2023-02-24 17:39:10,584][2364860] Loop rollout_proc12_evt_loop terminating... | |
| [2023-02-24 17:39:10,584][2364708] Component RolloutWorker_w12 stopped! | |
| [2023-02-24 17:39:10,583][2364859] Loop rollout_proc8_evt_loop terminating... | |
| [2023-02-24 17:39:10,585][2364708] Component RolloutWorker_w9 stopped! | |
| [2023-02-24 17:39:10,585][2364856] Stopping RolloutWorker_w9... | |
| [2023-02-24 17:39:10,585][2364856] Loop rollout_proc9_evt_loop terminating... | |
| [2023-02-24 17:39:10,585][2364708] Component RolloutWorker_w4 stopped! | |
| [2023-02-24 17:39:10,585][2364835] Stopping RolloutWorker_w4... | |
| [2023-02-24 17:39:10,586][2364835] Loop rollout_proc4_evt_loop terminating... | |
| [2023-02-24 17:39:10,591][2364831] Weights refcount: 2 0 | |
| [2023-02-24 17:39:10,596][2364831] Stopping InferenceWorker_p0-w0... | |
| [2023-02-24 17:39:10,596][2364708] Component InferenceWorker_p0-w0 stopped! | |
| [2023-02-24 17:39:10,596][2364831] Loop inference_proc0-0_evt_loop terminating... | |
| [2023-02-24 17:39:10,664][2364791] Removing /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000003287_13463552.pth | |
| [2023-02-24 17:39:10,667][2364837] Stopping RolloutWorker_w5... | |
| [2023-02-24 17:39:10,667][2364708] Component RolloutWorker_w5 stopped! | |
| [2023-02-24 17:39:10,667][2364837] Loop rollout_proc5_evt_loop terminating... | |
| [2023-02-24 17:39:10,675][2364791] Saving /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000004884_20004864.pth... | |
| [2023-02-24 17:39:10,679][2364834] Stopping RolloutWorker_w2... | |
| [2023-02-24 17:39:10,679][2364708] Component RolloutWorker_w2 stopped! | |
| [2023-02-24 17:39:10,679][2364834] Loop rollout_proc2_evt_loop terminating... | |
| [2023-02-24 17:39:10,810][2364791] Stopping LearnerWorker_p0... | |
| [2023-02-24 17:39:10,810][2364708] Component LearnerWorker_p0 stopped! | |
| [2023-02-24 17:39:10,811][2364791] Loop learner_proc0_evt_loop terminating... | |
| [2023-02-24 17:39:10,811][2364708] Waiting for process learner_proc0 to stop... | |
| [2023-02-24 17:39:11,642][2364708] Waiting for process inference_proc0-0 to join... | |
| [2023-02-24 17:39:11,642][2364708] Waiting for process rollout_proc0 to join... | |
| [2023-02-24 17:39:11,643][2364708] Waiting for process rollout_proc1 to join... | |
| [2023-02-24 17:39:11,643][2364708] Waiting for process rollout_proc2 to join... | |
| [2023-02-24 17:39:11,643][2364708] Waiting for process rollout_proc3 to join... | |
| [2023-02-24 17:39:11,643][2364708] Waiting for process rollout_proc4 to join... | |
| [2023-02-24 17:39:11,643][2364708] Waiting for process rollout_proc5 to join... | |
| [2023-02-24 17:39:11,644][2364708] Waiting for process rollout_proc6 to join... | |
| [2023-02-24 17:39:11,644][2364708] Waiting for process rollout_proc7 to join... | |
| [2023-02-24 17:39:11,644][2364708] Waiting for process rollout_proc8 to join... | |
| [2023-02-24 17:39:11,644][2364708] Waiting for process rollout_proc9 to join... | |
| [2023-02-24 17:39:11,644][2364708] Waiting for process rollout_proc10 to join... | |
| [2023-02-24 17:39:11,644][2364708] Waiting for process rollout_proc11 to join... | |
| [2023-02-24 17:39:11,644][2364708] Waiting for process rollout_proc12 to join... | |
| [2023-02-24 17:39:11,645][2364708] Waiting for process rollout_proc13 to join... | |
| [2023-02-24 17:39:11,645][2364708] Waiting for process rollout_proc14 to join... | |
| [2023-02-24 17:39:11,645][2364708] Waiting for process rollout_proc15 to join... | |
| [2023-02-24 17:39:11,645][2364708] Batcher 0 profile tree view: | |
| batching: 73.4519, releasing_batches: 0.1153 | |
| [2023-02-24 17:39:11,645][2364708] InferenceWorker_p0-w0 profile tree view: | |
| wait_policy: 0.0001 | |
| wait_policy_total: 14.4354 | |
| update_model: 8.0668 | |
| weight_update: 0.0009 | |
| one_step: 0.0083 | |
| handle_policy_step: 352.4861 | |
| deserialize: 37.8441, stack: 1.8339, obs_to_device_normalize: 110.8509, forward: 112.2633, send_messages: 30.0739 | |
| prepare_outputs: 46.8292 | |
| to_cpu: 31.2023 | |
| [2023-02-24 17:39:11,646][2364708] Learner 0 profile tree view: | |
| misc: 0.0142, prepare_batch: 21.8985 | |
| train: 88.0533 | |
| epoch_init: 0.0176, minibatch_init: 0.0202, losses_postprocess: 1.0969, kl_divergence: 0.8556, after_optimizer: 0.9595 | |
| calculate_losses: 27.5889 | |
| losses_init: 0.0102, forward_head: 2.8021, bptt_initial: 14.7305, tail: 1.9333, advantages_returns: 0.5209, losses: 3.3108 | |
| bptt: 3.7098 | |
| bptt_forward_core: 3.5507 | |
| update: 56.2303 | |
| clip: 3.0247 | |
| [2023-02-24 17:39:11,646][2364708] RolloutWorker_w0 profile tree view: | |
| wait_for_trajectories: 0.1784, enqueue_policy_requests: 13.5703, env_step: 193.6379, overhead: 19.5570, complete_rollouts: 0.3859 | |
| save_policy_outputs: 14.2004 | |
| split_output_tensors: 6.7511 | |
| [2023-02-24 17:39:11,646][2364708] RolloutWorker_w15 profile tree view: | |
| wait_for_trajectories: 0.1858, enqueue_policy_requests: 14.0534, env_step: 199.4115, overhead: 20.2979, complete_rollouts: 0.3205 | |
| save_policy_outputs: 14.6899 | |
| split_output_tensors: 6.9819 | |
| [2023-02-24 17:39:11,646][2364708] Loop Runner_EvtLoop terminating... | |
| [2023-02-24 17:39:11,646][2364708] Runner profile tree view: | |
| main_loop: 398.6762 | |
| [2023-02-24 17:39:11,647][2364708] Collected {0: 20004864}, FPS: 40130.2 | |
| [2023-02-24 17:39:11,652][2364708] Loading existing experiment configuration from train_dir/default_experiment/config.json | |
| [2023-02-24 17:39:11,652][2364708] Overriding arg 'train_dir' with value 'train_dir' passed from command line | |
| [2023-02-24 17:39:11,652][2364708] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2023-02-24 17:39:11,652][2364708] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2023-02-24 17:39:11,652][2364708] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2023-02-24 17:39:11,652][2364708] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-02-24 17:39:11,652][2364708] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2023-02-24 17:39:11,652][2364708] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-02-24 17:39:11,653][2364708] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2023-02-24 17:39:11,653][2364708] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2023-02-24 17:39:11,653][2364708] Adding new argument 'hf_repository'='eldraco/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2023-02-24 17:39:11,653][2364708] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2023-02-24 17:39:11,653][2364708] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2023-02-24 17:39:11,653][2364708] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2023-02-24 17:39:11,653][2364708] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2023-02-24 17:39:11,653][2364708] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2023-02-24 17:39:11,659][2364708] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:39:11,659][2364708] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-24 17:39:11,660][2364708] RunningMeanStd input shape: (1,) | |
| [2023-02-24 17:39:11,667][2364708] ConvEncoder: input_channels=3 | |
| [2023-02-24 17:39:11,779][2364708] Conv encoder output size: 512 | |
| [2023-02-24 17:39:11,779][2364708] Policy head output size: 512 | |
| [2023-02-24 17:39:13,104][2364708] Loading state from checkpoint train_dir/default_experiment/checkpoint_p0/checkpoint_000004884_20004864.pth... | |
| [2023-02-24 17:39:13,883][2364708] Num frames 100... | |
| [2023-02-24 17:39:13,953][2364708] Num frames 200... | |
| [2023-02-24 17:39:14,021][2364708] Num frames 300... | |
| [2023-02-24 17:39:14,089][2364708] Num frames 400... | |
| [2023-02-24 17:39:14,160][2364708] Num frames 500... | |
| [2023-02-24 17:39:14,229][2364708] Num frames 600... | |
| [2023-02-24 17:39:14,297][2364708] Num frames 700... | |
| [2023-02-24 17:39:14,365][2364708] Num frames 800... | |
| [2023-02-24 17:39:14,435][2364708] Num frames 900... | |
| [2023-02-24 17:39:14,505][2364708] Num frames 1000... | |
| [2023-02-24 17:39:14,575][2364708] Num frames 1100... | |
| [2023-02-24 17:39:14,645][2364708] Num frames 1200... | |
| [2023-02-24 17:39:14,714][2364708] Num frames 1300... | |
| [2023-02-24 17:39:14,784][2364708] Num frames 1400... | |
| [2023-02-24 17:39:14,886][2364708] Avg episode rewards: #0: 34.720, true rewards: #0: 14.720 | |
| [2023-02-24 17:39:14,887][2364708] Avg episode reward: 34.720, avg true_objective: 14.720 | |
| [2023-02-24 17:39:14,917][2364708] Num frames 1500... | |
| [2023-02-24 17:39:14,998][2364708] Num frames 1600... | |
| [2023-02-24 17:39:15,067][2364708] Num frames 1700... | |
| [2023-02-24 17:39:15,138][2364708] Num frames 1800... | |
| [2023-02-24 17:39:15,208][2364708] Num frames 1900... | |
| [2023-02-24 17:39:15,277][2364708] Num frames 2000... | |
| [2023-02-24 17:39:15,347][2364708] Num frames 2100... | |
| [2023-02-24 17:39:15,415][2364708] Num frames 2200... | |
| [2023-02-24 17:39:15,485][2364708] Num frames 2300... | |
| [2023-02-24 17:39:15,554][2364708] Num frames 2400... | |
| [2023-02-24 17:39:15,621][2364708] Num frames 2500... | |
| [2023-02-24 17:39:15,714][2364708] Avg episode rewards: #0: 31.300, true rewards: #0: 12.800 | |
| [2023-02-24 17:39:15,715][2364708] Avg episode reward: 31.300, avg true_objective: 12.800 | |
| [2023-02-24 17:39:15,758][2364708] Num frames 2600... | |
| [2023-02-24 17:39:15,831][2364708] Num frames 2700... | |
| [2023-02-24 17:39:15,900][2364708] Num frames 2800... | |
| [2023-02-24 17:39:15,969][2364708] Num frames 2900... | |
| [2023-02-24 17:39:16,037][2364708] Num frames 3000... | |
| [2023-02-24 17:39:16,106][2364708] Num frames 3100... | |
| [2023-02-24 17:39:16,177][2364708] Num frames 3200... | |
| [2023-02-24 17:39:16,247][2364708] Num frames 3300... | |
| [2023-02-24 17:39:16,316][2364708] Num frames 3400... | |
| [2023-02-24 17:39:16,386][2364708] Num frames 3500... | |
| [2023-02-24 17:39:16,455][2364708] Num frames 3600... | |
| [2023-02-24 17:39:16,526][2364708] Num frames 3700... | |
| [2023-02-24 17:39:16,596][2364708] Num frames 3800... | |
| [2023-02-24 17:39:16,665][2364708] Num frames 3900... | |
| [2023-02-24 17:39:16,734][2364708] Num frames 4000... | |
| [2023-02-24 17:39:16,802][2364708] Num frames 4100... | |
| [2023-02-24 17:39:16,871][2364708] Num frames 4200... | |
| [2023-02-24 17:39:16,941][2364708] Num frames 4300... | |
| [2023-02-24 17:39:17,010][2364708] Num frames 4400... | |
| [2023-02-24 17:39:17,078][2364708] Num frames 4500... | |
| [2023-02-24 17:39:17,148][2364708] Num frames 4600... | |
| [2023-02-24 17:39:17,244][2364708] Avg episode rewards: #0: 41.533, true rewards: #0: 15.533 | |
| [2023-02-24 17:39:17,244][2364708] Avg episode reward: 41.533, avg true_objective: 15.533 | |
| [2023-02-24 17:39:17,288][2364708] Num frames 4700... | |
| [2023-02-24 17:39:17,360][2364708] Num frames 4800... | |
| [2023-02-24 17:39:17,430][2364708] Num frames 4900... | |
| [2023-02-24 17:39:17,499][2364708] Num frames 5000... | |
| [2023-02-24 17:39:17,569][2364708] Num frames 5100... | |
| [2023-02-24 17:39:17,640][2364708] Num frames 5200... | |
| [2023-02-24 17:39:17,720][2364708] Avg episode rewards: #0: 34.100, true rewards: #0: 13.100 | |
| [2023-02-24 17:39:17,720][2364708] Avg episode reward: 34.100, avg true_objective: 13.100 | |
| [2023-02-24 17:39:17,789][2364708] Num frames 5300... | |
| [2023-02-24 17:39:17,857][2364708] Num frames 5400... | |
| [2023-02-24 17:39:17,926][2364708] Num frames 5500... | |
| [2023-02-24 17:39:17,995][2364708] Num frames 5600... | |
| [2023-02-24 17:39:18,063][2364708] Num frames 5700... | |
| [2023-02-24 17:39:18,132][2364708] Num frames 5800... | |
| [2023-02-24 17:39:18,195][2364708] Avg episode rewards: #0: 29.232, true rewards: #0: 11.632 | |
| [2023-02-24 17:39:18,195][2364708] Avg episode reward: 29.232, avg true_objective: 11.632 | |
| [2023-02-24 17:39:18,273][2364708] Num frames 5900... | |
| [2023-02-24 17:39:18,342][2364708] Num frames 6000... | |
| [2023-02-24 17:39:18,409][2364708] Num frames 6100... | |
| [2023-02-24 17:39:18,482][2364708] Num frames 6200... | |
| [2023-02-24 17:39:18,552][2364708] Num frames 6300... | |
| [2023-02-24 17:39:18,646][2364708] Avg episode rewards: #0: 25.600, true rewards: #0: 10.600 | |
| [2023-02-24 17:39:18,646][2364708] Avg episode reward: 25.600, avg true_objective: 10.600 | |
| [2023-02-24 17:39:18,691][2364708] Num frames 6400... | |
| [2023-02-24 17:39:18,767][2364708] Num frames 6500... | |
| [2023-02-24 17:39:18,835][2364708] Num frames 6600... | |
| [2023-02-24 17:39:18,904][2364708] Num frames 6700... | |
| [2023-02-24 17:39:18,972][2364708] Num frames 6800... | |
| [2023-02-24 17:39:19,041][2364708] Num frames 6900... | |
| [2023-02-24 17:39:19,110][2364708] Num frames 7000... | |
| [2023-02-24 17:39:19,179][2364708] Num frames 7100... | |
| [2023-02-24 17:39:19,249][2364708] Num frames 7200... | |
| [2023-02-24 17:39:19,318][2364708] Num frames 7300... | |
| [2023-02-24 17:39:19,388][2364708] Num frames 7400... | |
| [2023-02-24 17:39:19,458][2364708] Num frames 7500... | |
| [2023-02-24 17:39:19,528][2364708] Num frames 7600... | |
| [2023-02-24 17:39:19,598][2364708] Num frames 7700... | |
| [2023-02-24 17:39:19,667][2364708] Num frames 7800... | |
| [2023-02-24 17:39:19,736][2364708] Num frames 7900... | |
| [2023-02-24 17:39:19,808][2364708] Avg episode rewards: #0: 28.040, true rewards: #0: 11.326 | |
| [2023-02-24 17:39:19,808][2364708] Avg episode reward: 28.040, avg true_objective: 11.326 | |
| [2023-02-24 17:39:19,879][2364708] Num frames 8000... | |
| [2023-02-24 17:39:19,948][2364708] Num frames 8100... | |
| [2023-02-24 17:39:20,017][2364708] Num frames 8200... | |
| [2023-02-24 17:39:20,086][2364708] Num frames 8300... | |
| [2023-02-24 17:39:20,155][2364708] Num frames 8400... | |
| [2023-02-24 17:39:20,225][2364708] Num frames 8500... | |
| [2023-02-24 17:39:20,294][2364708] Num frames 8600... | |
| [2023-02-24 17:39:20,363][2364708] Num frames 8700... | |
| [2023-02-24 17:39:20,432][2364708] Num frames 8800... | |
| [2023-02-24 17:39:20,501][2364708] Num frames 8900... | |
| [2023-02-24 17:39:20,571][2364708] Num frames 9000... | |
| [2023-02-24 17:39:20,640][2364708] Num frames 9100... | |
| [2023-02-24 17:39:20,711][2364708] Num frames 9200... | |
| [2023-02-24 17:39:20,781][2364708] Num frames 9300... | |
| [2023-02-24 17:39:20,850][2364708] Num frames 9400... | |
| [2023-02-24 17:39:20,919][2364708] Num frames 9500... | |
| [2023-02-24 17:39:20,990][2364708] Num frames 9600... | |
| [2023-02-24 17:39:21,060][2364708] Num frames 9700... | |
| [2023-02-24 17:39:21,130][2364708] Num frames 9800... | |
| [2023-02-24 17:39:21,198][2364708] Num frames 9900... | |
| [2023-02-24 17:39:21,269][2364708] Num frames 10000... | |
| [2023-02-24 17:39:21,341][2364708] Avg episode rewards: #0: 32.035, true rewards: #0: 12.535 | |
| [2023-02-24 17:39:21,341][2364708] Avg episode reward: 32.035, avg true_objective: 12.535 | |
| [2023-02-24 17:39:21,412][2364708] Num frames 10100... | |
| [2023-02-24 17:39:21,481][2364708] Num frames 10200... | |
| [2023-02-24 17:39:21,551][2364708] Num frames 10300... | |
| [2023-02-24 17:39:21,621][2364708] Num frames 10400... | |
| [2023-02-24 17:39:21,691][2364708] Num frames 10500... | |
| [2023-02-24 17:39:21,759][2364708] Num frames 10600... | |
| [2023-02-24 17:39:21,828][2364708] Num frames 10700... | |
| [2023-02-24 17:39:21,897][2364708] Num frames 10800... | |
| [2023-02-24 17:39:21,966][2364708] Num frames 10900... | |
| [2023-02-24 17:39:22,035][2364708] Num frames 11000... | |
| [2023-02-24 17:39:22,117][2364708] Avg episode rewards: #0: 31.603, true rewards: #0: 12.270 | |
| [2023-02-24 17:39:22,118][2364708] Avg episode reward: 31.603, avg true_objective: 12.270 | |
| [2023-02-24 17:39:22,180][2364708] Num frames 11100... | |
| [2023-02-24 17:39:22,251][2364708] Num frames 11200... | |
| [2023-02-24 17:39:22,320][2364708] Num frames 11300... | |
| [2023-02-24 17:39:22,389][2364708] Num frames 11400... | |
| [2023-02-24 17:39:22,458][2364708] Num frames 11500... | |
| [2023-02-24 17:39:22,527][2364708] Num frames 11600... | |
| [2023-02-24 17:39:22,596][2364708] Num frames 11700... | |
| [2023-02-24 17:39:22,666][2364708] Num frames 11800... | |
| [2023-02-24 17:39:22,735][2364708] Num frames 11900... | |
| [2023-02-24 17:39:22,804][2364708] Num frames 12000... | |
| [2023-02-24 17:39:22,874][2364708] Num frames 12100... | |
| [2023-02-24 17:39:22,944][2364708] Num frames 12200... | |
| [2023-02-24 17:39:23,013][2364708] Num frames 12300... | |
| [2023-02-24 17:39:23,082][2364708] Num frames 12400... | |
| [2023-02-24 17:39:23,152][2364708] Num frames 12500... | |
| [2023-02-24 17:39:23,220][2364708] Num frames 12600... | |
| [2023-02-24 17:39:23,289][2364708] Num frames 12700... | |
| [2023-02-24 17:39:23,360][2364708] Num frames 12800... | |
| [2023-02-24 17:39:23,433][2364708] Avg episode rewards: #0: 33.229, true rewards: #0: 12.829 | |
| [2023-02-24 17:39:23,433][2364708] Avg episode reward: 33.229, avg true_objective: 12.829 | |
| [2023-02-24 17:39:39,087][2364708] Replay video saved to train_dir/default_experiment/replay.mp4! | |