ppo-Huggy / run_logs /timers.json
Dimba777's picture
Huggy
eaccff0 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4074351787567139,
"min": 1.4074351787567139,
"max": 1.4269214868545532,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71047.328125,
"min": 69154.0625,
"max": 76891.640625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 77.00778816199377,
"min": 77.00778816199377,
"max": 383.07575757575756,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49439.0,
"min": 49036.0,
"max": 50566.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999961.0,
"min": 49949.0,
"max": 1999961.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999961.0,
"min": 49949.0,
"max": 1999961.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.481337070465088,
"min": 0.13142752647399902,
"max": 2.5003163814544678,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1593.0184326171875,
"min": 17.21700668334961,
"max": 1593.0184326171875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8160043400581753,
"min": 1.8545301442837898,
"max": 3.967038714288599,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2449.8747863173485,
"min": 242.94344890117645,
"max": 2449.8747863173485,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8160043400581753,
"min": 1.8545301442837898,
"max": 3.967038714288599,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2449.8747863173485,
"min": 242.94344890117645,
"max": 2449.8747863173485,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.020411397133850387,
"min": 0.013977931653304645,
"max": 0.020411397133850387,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.06123419140155116,
"min": 0.02795586330660929,
"max": 0.06123419140155116,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06072985542317232,
"min": 0.022727929738660654,
"max": 0.06644596296052138,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18218956626951696,
"min": 0.04545585947732131,
"max": 0.19933788888156415,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.607798797433336e-06,
"min": 3.607798797433336e-06,
"max": 0.00029532015155995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0823396392300007e-05,
"min": 1.0823396392300007e-05,
"max": 0.0008438962687012498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10120256666666672,
"min": 0.10120256666666672,
"max": 0.19844004999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30360770000000015,
"min": 0.20753629999999995,
"max": 0.5812987500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.000807666666672e-05,
"min": 7.000807666666672e-05,
"max": 0.004922158495,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021002423000000015,
"min": 0.00021002423000000015,
"max": 0.014066807624999997,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1740663955",
"python_version": "3.10.12 (main, Feb 4 2025, 14:57:36) [GCC 11.4.0]",
"command_line_arguments": "/home/dbarbashin/venvs_user/rl_huggi/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1740665587"
},
"total": 1547.4642846039787,
"count": 1,
"self": 0.16780203697271645,
"children": {
"run_training.setup": {
"total": 0.011743932001991197,
"count": 1,
"self": 0.011743932001991197
},
"TrainerController.start_learning": {
"total": 1547.284738635004,
"count": 1,
"self": 2.2262143454281613,
"children": {
"TrainerController._reset_env": {
"total": 1.17032554699108,
"count": 1,
"self": 1.17032554699108
},
"TrainerController.advance": {
"total": 1543.7958469975856,
"count": 232647,
"self": 1.9497660558263306,
"children": {
"env_step": {
"total": 1279.6708151576458,
"count": 232647,
"self": 758.7538405227533,
"children": {
"SubprocessEnvManager._take_step": {
"total": 519.3797313375399,
"count": 232647,
"self": 8.10353729093913,
"children": {
"TorchPolicy.evaluate": {
"total": 511.2761940466007,
"count": 222940,
"self": 511.2761940466007
}
}
},
"workers": {
"total": 1.5372432973526884,
"count": 232647,
"self": 0.0,
"children": {
"worker_root": {
"total": 1542.1813472905487,
"count": 232647,
"is_parallel": true,
"self": 905.6730805405823,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0005512050120159984,
"count": 1,
"is_parallel": true,
"self": 0.00012928800424560905,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004219170077703893,
"count": 2,
"is_parallel": true,
"self": 0.0004219170077703893
}
}
},
"UnityEnvironment.step": {
"total": 0.010739505989477038,
"count": 1,
"is_parallel": true,
"self": 0.00012020999565720558,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 9.397801477462053e-05,
"count": 1,
"is_parallel": true,
"self": 9.397801477462053e-05
},
"communicator.exchange": {
"total": 0.01031017699278891,
"count": 1,
"is_parallel": true,
"self": 0.01031017699278891
},
"steps_from_proto": {
"total": 0.0002151409862563014,
"count": 1,
"is_parallel": true,
"self": 5.046301521360874e-05,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00016467797104269266,
"count": 2,
"is_parallel": true,
"self": 0.00016467797104269266
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 636.5082667499664,
"count": 232646,
"is_parallel": true,
"self": 12.036409309162991,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 19.83041047854931,
"count": 232646,
"is_parallel": true,
"self": 19.83041047854931
},
"communicator.exchange": {
"total": 578.9103023134521,
"count": 232646,
"is_parallel": true,
"self": 578.9103023134521
},
"steps_from_proto": {
"total": 25.731144648802,
"count": 232646,
"is_parallel": true,
"self": 8.379888311581453,
"children": {
"_process_rank_one_or_two_observation": {
"total": 17.351256337220548,
"count": 465292,
"is_parallel": true,
"self": 17.351256337220548
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 262.17526578411344,
"count": 232647,
"self": 3.3136255825229455,
"children": {
"process_trajectory": {
"total": 104.25902222463628,
"count": 232647,
"self": 103.31972998857964,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9392922360566445,
"count": 10,
"self": 0.9392922360566445
}
}
},
"_update_policy": {
"total": 154.6026179769542,
"count": 97,
"self": 89.24647272293805,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.35614525401616,
"count": 2910,
"self": 65.35614525401616
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.530003596097231e-07,
"count": 1,
"self": 3.530003596097231e-07
},
"TrainerController._save_models": {
"total": 0.09235139199881814,
"count": 1,
"self": 0.0007827510125935078,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09156864098622464,
"count": 1,
"self": 0.09156864098622464
}
}
}
}
}
}
}