ppo-Huggy / run_logs /timers.json
Minazor's picture
Huggy
02b4e1a verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4057433605194092,
"min": 1.4057433605194092,
"max": 1.426342487335205,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71900.9609375,
"min": 68425.03125,
"max": 76091.40625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 84.85934819897084,
"min": 80.39024390243902,
"max": 429.28205128205127,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49473.0,
"min": 48772.0,
"max": 50277.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999980.0,
"min": 49609.0,
"max": 1999980.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999980.0,
"min": 49609.0,
"max": 1999980.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4340620040893555,
"min": 0.02215196006000042,
"max": 2.464726448059082,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1419.05810546875,
"min": 2.569627285003662,
"max": 1499.13916015625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7711269217535315,
"min": 1.722770657775731,
"max": 3.8807142883881753,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2198.566995382309,
"min": 199.8413963019848,
"max": 2329.462767660618,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7711269217535315,
"min": 1.722770657775731,
"max": 3.8807142883881753,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2198.566995382309,
"min": 199.8413963019848,
"max": 2329.462767660618,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01792765732809332,
"min": 0.013142177786357935,
"max": 0.02040930035808641,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05378297198427996,
"min": 0.02628435557271587,
"max": 0.061227901074259225,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05972303905420834,
"min": 0.023617149920513232,
"max": 0.06105915295581023,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.179169117162625,
"min": 0.047234299841026464,
"max": 0.1793866191059351,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3531488823166686e-06,
"min": 3.3531488823166686e-06,
"max": 0.0002953809015396999,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0059446646950006e-05,
"min": 1.0059446646950006e-05,
"max": 0.0008439424686858498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10111768333333333,
"min": 0.10111768333333333,
"max": 0.19846030000000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30335305,
"min": 0.20736295000000005,
"max": 0.5813141500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.577239833333335e-05,
"min": 6.577239833333335e-05,
"max": 0.00492316897,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019731719500000006,
"min": 0.00019731719500000006,
"max": 0.014067576084999995,
"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": "1719389121",
"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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1719391719"
},
"total": 2598.516924999,
"count": 1,
"self": 0.7351863640001284,
"children": {
"run_training.setup": {
"total": 0.05690289500000745,
"count": 1,
"self": 0.05690289500000745
},
"TrainerController.start_learning": {
"total": 2597.72483574,
"count": 1,
"self": 4.786338192938729,
"children": {
"TrainerController._reset_env": {
"total": 3.1460707100000036,
"count": 1,
"self": 3.1460707100000036
},
"TrainerController.advance": {
"total": 2589.604793201061,
"count": 232326,
"self": 5.0791743402505745,
"children": {
"env_step": {
"total": 2045.8718447288798,
"count": 232326,
"self": 1690.4327222409058,
"children": {
"SubprocessEnvManager._take_step": {
"total": 352.2422709679571,
"count": 232326,
"self": 18.922981186894106,
"children": {
"TorchPolicy.evaluate": {
"total": 333.319289781063,
"count": 222974,
"self": 333.319289781063
}
}
},
"workers": {
"total": 3.1968515200168213,
"count": 232326,
"self": 0.0,
"children": {
"worker_root": {
"total": 2589.9837068109005,
"count": 232326,
"is_parallel": true,
"self": 1229.0406861968884,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010270539999623907,
"count": 1,
"is_parallel": true,
"self": 0.000350476999926741,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006765770000356497,
"count": 2,
"is_parallel": true,
"self": 0.0006765770000356497
}
}
},
"UnityEnvironment.step": {
"total": 0.0303147660000036,
"count": 1,
"is_parallel": true,
"self": 0.00043422000004511574,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021813799997971728,
"count": 1,
"is_parallel": true,
"self": 0.00021813799997971728
},
"communicator.exchange": {
"total": 0.028814269000008608,
"count": 1,
"is_parallel": true,
"self": 0.028814269000008608
},
"steps_from_proto": {
"total": 0.0008481389999701605,
"count": 1,
"is_parallel": true,
"self": 0.00021811699997442702,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006300219999957335,
"count": 2,
"is_parallel": true,
"self": 0.0006300219999957335
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1360.943020614012,
"count": 232325,
"is_parallel": true,
"self": 41.40702736999242,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 88.8605869400846,
"count": 232325,
"is_parallel": true,
"self": 88.8605869400846
},
"communicator.exchange": {
"total": 1133.1835757059248,
"count": 232325,
"is_parallel": true,
"self": 1133.1835757059248
},
"steps_from_proto": {
"total": 97.49183059801027,
"count": 232325,
"is_parallel": true,
"self": 37.088290996031276,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.40353960197899,
"count": 464650,
"is_parallel": true,
"self": 60.40353960197899
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 538.6537741319307,
"count": 232326,
"self": 7.314022250041944,
"children": {
"process_trajectory": {
"total": 166.4893090428891,
"count": 232326,
"self": 165.0989973838889,
"children": {
"RLTrainer._checkpoint": {
"total": 1.39031165900019,
"count": 10,
"self": 1.39031165900019
}
}
},
"_update_policy": {
"total": 364.8504428389997,
"count": 97,
"self": 297.4786292430116,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.3718135959881,
"count": 2910,
"self": 67.3718135959881
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.835000148275867e-06,
"count": 1,
"self": 1.835000148275867e-06
},
"TrainerController._save_models": {
"total": 0.18763180099995225,
"count": 1,
"self": 0.005557111000143777,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18207468999980847,
"count": 1,
"self": 0.18207468999980847
}
}
}
}
}
}
}