{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4011120796203613, "min": 1.4011120796203613, "max": 1.4269287586212158, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70935.5, "min": 69269.953125, "max": 77364.6015625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 71.71075581395348, "min": 71.71075581395348, "max": 426.77777777777777, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49337.0, "min": 49207.0, "max": 49964.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999990.0, "min": 49916.0, "max": 1999990.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999990.0, "min": 49916.0, "max": 1999990.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.462876558303833, "min": 0.017916562035679817, "max": 2.490422487258911, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1694.4591064453125, "min": 2.0783212184906006, "max": 1694.4591064453125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8731634609921035, "min": 1.9489738535264443, "max": 4.00330705236772, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2664.736461162567, "min": 226.08096700906754, "max": 2664.736461162567, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8731634609921035, "min": 1.9489738535264443, "max": 4.00330705236772, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2664.736461162567, "min": 226.08096700906754, "max": 2664.736461162567, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01678521316498518, "min": 0.0129947999259457, "max": 0.019882318120734353, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.050355639494955536, "min": 0.0259895998518914, "max": 0.05964695436220306, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05998852306769955, "min": 0.02226441049327453, "max": 0.06109367677321037, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17996556920309864, "min": 0.04452882098654906, "max": 0.17996556920309864, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.596148801316662e-06, "min": 3.596148801316662e-06, "max": 0.0002953518765493751, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0788446403949986e-05, "min": 1.0788446403949986e-05, "max": 0.0008440557186480999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10119868333333337, "min": 0.10119868333333337, "max": 0.198450625, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3035960500000001, "min": 0.20753645000000004, "max": 0.5813518999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.981429833333328e-05, "min": 6.981429833333328e-05, "max": 0.004922686187499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020944289499999984, "min": 0.00020944289499999984, "max": 0.014069459810000002, "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": "1739620204", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/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": "1739622880" }, "total": 2676.408976909, "count": 1, "self": 0.4428963250002198, "children": { "run_training.setup": { "total": 0.02555931100005182, "count": 1, "self": 0.02555931100005182 }, "TrainerController.start_learning": { "total": 2675.940521273, "count": 1, "self": 4.737380871021287, "children": { "TrainerController._reset_env": { "total": 3.3632820409998203, "count": 1, "self": 3.3632820409998203 }, "TrainerController.advance": { "total": 2667.6875398549782, "count": 233056, "self": 5.300682650822637, "children": { "env_step": { "total": 2156.050692878107, "count": 233056, "self": 1689.9362006508684, "children": { "SubprocessEnvManager._take_step": { "total": 463.1628452750408, "count": 233056, "self": 16.835060560033526, "children": { "TorchPolicy.evaluate": { "total": 446.3277847150073, "count": 222950, "self": 446.3277847150073 } } }, "workers": { "total": 2.951646952197734, "count": 233056, "self": 0.0, "children": { "worker_root": { "total": 2667.738603651155, "count": 233056, "is_parallel": true, "self": 1292.1660367170673, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012191600001187908, "count": 1, "is_parallel": true, "self": 0.0004905900000267138, "children": { "_process_rank_one_or_two_observation": { "total": 0.000728570000092077, "count": 2, "is_parallel": true, "self": 0.000728570000092077 } } }, "UnityEnvironment.step": { "total": 0.06927119699980722, "count": 1, "is_parallel": true, "self": 0.00031590800017511356, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021195799990891828, "count": 1, "is_parallel": true, "self": 0.00021195799990891828 }, "communicator.exchange": { "total": 0.06797182399986923, "count": 1, "is_parallel": true, "self": 0.06797182399986923 }, "steps_from_proto": { "total": 0.0007715069998539548, "count": 1, "is_parallel": true, "self": 0.00018366299968874955, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005878440001652052, "count": 2, "is_parallel": true, "self": 0.0005878440001652052 } } } } } } }, "UnityEnvironment.step": { "total": 1375.5725669340875, "count": 233055, "is_parallel": true, "self": 40.089346689140484, "children": { "UnityEnvironment._generate_step_input": { "total": 89.98964662912817, "count": 233055, "is_parallel": true, "self": 89.98964662912817 }, "communicator.exchange": { "total": 1151.153742505946, "count": 233055, "is_parallel": true, "self": 1151.153742505946 }, "steps_from_proto": { "total": 94.33983110987288, "count": 233055, "is_parallel": true, "self": 35.83557349390321, "children": { "_process_rank_one_or_two_observation": { "total": 58.504257615969664, "count": 466110, "is_parallel": true, "self": 58.504257615969664 } } } } } } } } } } }, "trainer_advance": { "total": 506.3361643260489, "count": 233056, "self": 6.733564573062722, "children": { "process_trajectory": { "total": 184.76026549698554, "count": 233056, "self": 183.1409719919859, "children": { "RLTrainer._checkpoint": { "total": 1.6192935049996322, "count": 10, "self": 1.6192935049996322 } } }, "_update_policy": { "total": 314.84233425600064, "count": 97, "self": 249.92581892198746, "children": { "TorchPPOOptimizer.update": { "total": 64.91651533401318, "count": 2910, "self": 64.91651533401318 } } } } } } }, "trainer_threads": { "total": 1.2190002962597646e-06, "count": 1, "self": 1.2190002962597646e-06 }, "TrainerController._save_models": { "total": 0.1523172870001872, "count": 1, "self": 0.0022277279995250865, "children": { "RLTrainer._checkpoint": { "total": 0.15008955900066212, "count": 1, "self": 0.15008955900066212 } } } } } } }