{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4055540561676025, "min": 1.4055540561676025, "max": 1.429126501083374, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71764.78125, "min": 67542.6953125, "max": 77949.0703125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 86.82425307557118, "min": 86.82425307557118, "max": 370.20588235294116, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49403.0, "min": 49101.0, "max": 50348.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999934.0, "min": 49735.0, "max": 1999934.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999934.0, "min": 49735.0, "max": 1999934.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3646011352539062, "min": 0.0360133983194828, "max": 2.39609956741333, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1345.4580078125, "min": 4.861808776855469, "max": 1345.4580078125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6920034108136783, "min": 1.698002999579465, "max": 3.868579069961859, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2100.749940752983, "min": 229.23040494322777, "max": 2100.749940752983, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6920034108136783, "min": 1.698002999579465, "max": 3.868579069961859, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2100.749940752983, "min": 229.23040494322777, "max": 2100.749940752983, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018750641424170073, "min": 0.013849271166933855, "max": 0.019616261201645103, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.037501282848340145, "min": 0.02769854233386771, "max": 0.057611091464059426, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.061620008386671546, "min": 0.02398603142549594, "max": 0.06257299073040486, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.12324001677334309, "min": 0.048551933653652665, "max": 0.16076049792269864, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.318448560550009e-06, "min": 4.318448560550009e-06, "max": 0.000295294876568375, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.636897121100018e-06, "min": 8.636897121100018e-06, "max": 0.0008435392688202498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10143945000000001, "min": 0.10143945000000001, "max": 0.198431625, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20287890000000003, "min": 0.20287890000000003, "max": 0.5811797500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.182855500000016e-05, "min": 8.182855500000016e-05, "max": 0.0049217380875000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00016365711000000031, "min": 0.00016365711000000031, "max": 0.014060869524999998, "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": "1714540414", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714542936" }, "total": 2522.338966989, "count": 1, "self": 0.4735331699998824, "children": { "run_training.setup": { "total": 0.05625510999999506, "count": 1, "self": 0.05625510999999506 }, "TrainerController.start_learning": { "total": 2521.8091787089998, "count": 1, "self": 4.458102462077477, "children": { "TrainerController._reset_env": { "total": 2.968715025999984, "count": 1, "self": 2.968715025999984 }, "TrainerController.advance": { "total": 2514.266868365922, "count": 231349, "self": 4.814550600046914, "children": { "env_step": { "total": 2031.2423240159442, "count": 231349, "self": 1681.9598673428475, "children": { "SubprocessEnvManager._take_step": { "total": 346.08179636000006, "count": 231349, "self": 18.840431750039897, "children": { "TorchPolicy.evaluate": { "total": 327.24136460996016, "count": 222938, "self": 327.24136460996016 } } }, "workers": { "total": 3.2006603130966482, "count": 231349, "self": 0.0, "children": { "worker_root": { "total": 2514.19584628799, "count": 231349, "is_parallel": true, "self": 1162.2318478479995, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009680240000307094, "count": 1, "is_parallel": true, "self": 0.00025855500007310184, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007094689999576076, "count": 2, "is_parallel": true, "self": 0.0007094689999576076 } } }, "UnityEnvironment.step": { "total": 0.0353508939999756, "count": 1, "is_parallel": true, "self": 0.0004119489999538928, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002514490000180558, "count": 1, "is_parallel": true, "self": 0.0002514490000180558 }, "communicator.exchange": { "total": 0.033823449999999866, "count": 1, "is_parallel": true, "self": 0.033823449999999866 }, "steps_from_proto": { "total": 0.000864046000003782, "count": 1, "is_parallel": true, "self": 0.0002556659999299882, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006083800000737938, "count": 2, "is_parallel": true, "self": 0.0006083800000737938 } } } } } } }, "UnityEnvironment.step": { "total": 1351.9639984399907, "count": 231348, "is_parallel": true, "self": 41.04177306198062, "children": { "UnityEnvironment._generate_step_input": { "total": 90.52730724498218, "count": 231348, "is_parallel": true, "self": 90.52730724498218 }, "communicator.exchange": { "total": 1123.284158936975, "count": 231348, "is_parallel": true, "self": 1123.284158936975 }, "steps_from_proto": { "total": 97.11075919605287, "count": 231348, "is_parallel": true, "self": 36.94463072097204, "children": { "_process_rank_one_or_two_observation": { "total": 60.166128475080825, "count": 462696, "is_parallel": true, "self": 60.166128475080825 } } } } } } } } } } }, "trainer_advance": { "total": 478.2099937499309, "count": 231349, "self": 7.0203982498691175, "children": { "process_trajectory": { "total": 160.04558060506207, "count": 231349, "self": 158.66315983606245, "children": { "RLTrainer._checkpoint": { "total": 1.3824207689996229, "count": 10, "self": 1.3824207689996229 } } }, "_update_policy": { "total": 311.1440148949997, "count": 96, "self": 249.5141563400141, "children": { "TorchPPOOptimizer.update": { "total": 61.62985855498562, "count": 2880, "self": 61.62985855498562 } } } } } } }, "trainer_threads": { "total": 1.027000052999938e-06, "count": 1, "self": 1.027000052999938e-06 }, "TrainerController._save_models": { "total": 0.11549182799990376, "count": 1, "self": 0.0031832710001253872, "children": { "RLTrainer._checkpoint": { "total": 0.11230855699977838, "count": 1, "self": 0.11230855699977838 } } } } } } }