ppo-Huggy / run_logs /timers.json
pratsy's picture
Huggy
d0f6b4b
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4064899682998657,
"min": 1.4064854383468628,
"max": 1.4262715578079224,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71437.03125,
"min": 67822.5703125,
"max": 75924.0390625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 90.0783242258652,
"min": 82.60367892976589,
"max": 416.9166666666667,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49453.0,
"min": 49011.0,
"max": 50118.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999973.0,
"min": 49759.0,
"max": 1999973.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999973.0,
"min": 49759.0,
"max": 1999973.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.450319766998291,
"min": 0.04748943820595741,
"max": 2.5212624073028564,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1345.2255859375,
"min": 5.651243209838867,
"max": 1424.9581298828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7916242256624884,
"min": 1.6432950977517777,
"max": 3.958276013833658,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2081.601699888706,
"min": 195.55211663246155,
"max": 2228.2995309233665,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7916242256624884,
"min": 1.6432950977517777,
"max": 3.958276013833658,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2081.601699888706,
"min": 195.55211663246155,
"max": 2228.2995309233665,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014996415585564036,
"min": 0.013424618435480323,
"max": 0.01938797717933388,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04498924675669211,
"min": 0.029742667226916333,
"max": 0.05532293899984021,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.054614540313680966,
"min": 0.023121055526038013,
"max": 0.05850492641329766,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1638436209410429,
"min": 0.046242111052076026,
"max": 0.1665550631781419,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5464488178833313e-06,
"min": 3.5464488178833313e-06,
"max": 0.00029534955155014993,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0639346453649993e-05,
"min": 1.0639346453649993e-05,
"max": 0.00084407446864185,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10118211666666667,
"min": 0.10118211666666667,
"max": 0.19844985000000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30354635,
"min": 0.20750860000000004,
"max": 0.58135815,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.898762166666665e-05,
"min": 6.898762166666665e-05,
"max": 0.0049226475150000015,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020696286499999995,
"min": 0.00020696286499999995,
"max": 0.014069771685000003,
"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": "1688058803",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1688061221"
},
"total": 2418.405733335,
"count": 1,
"self": 0.45087275200057775,
"children": {
"run_training.setup": {
"total": 0.07057484999995722,
"count": 1,
"self": 0.07057484999995722
},
"TrainerController.start_learning": {
"total": 2417.8842857329996,
"count": 1,
"self": 4.419946082949082,
"children": {
"TrainerController._reset_env": {
"total": 4.636135921999994,
"count": 1,
"self": 4.636135921999994
},
"TrainerController.advance": {
"total": 2408.7027862990503,
"count": 232192,
"self": 4.567851282026368,
"children": {
"env_step": {
"total": 1876.991392971025,
"count": 232192,
"self": 1581.8782045281116,
"children": {
"SubprocessEnvManager._take_step": {
"total": 292.3021187910167,
"count": 232192,
"self": 16.40376035104282,
"children": {
"TorchPolicy.evaluate": {
"total": 275.8983584399739,
"count": 223028,
"self": 275.8983584399739
}
}
},
"workers": {
"total": 2.811069651896787,
"count": 232192,
"self": 0.0,
"children": {
"worker_root": {
"total": 2410.092154838934,
"count": 232192,
"is_parallel": true,
"self": 1119.7396252539247,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009583329999713897,
"count": 1,
"is_parallel": true,
"self": 0.0002604149999569927,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000697918000014397,
"count": 2,
"is_parallel": true,
"self": 0.000697918000014397
}
}
},
"UnityEnvironment.step": {
"total": 0.029088542999943456,
"count": 1,
"is_parallel": true,
"self": 0.00034279700003025937,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021959299999707582,
"count": 1,
"is_parallel": true,
"self": 0.00021959299999707582
},
"communicator.exchange": {
"total": 0.027768778999984534,
"count": 1,
"is_parallel": true,
"self": 0.027768778999984534
},
"steps_from_proto": {
"total": 0.0007573739999315876,
"count": 1,
"is_parallel": true,
"self": 0.00019828400002097624,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005590899999106114,
"count": 2,
"is_parallel": true,
"self": 0.0005590899999106114
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1290.3525295850095,
"count": 232191,
"is_parallel": true,
"self": 39.73960698001929,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.10453723309308,
"count": 232191,
"is_parallel": true,
"self": 78.10453723309308
},
"communicator.exchange": {
"total": 1076.3596271479844,
"count": 232191,
"is_parallel": true,
"self": 1076.3596271479844
},
"steps_from_proto": {
"total": 96.14875822391298,
"count": 232191,
"is_parallel": true,
"self": 33.69079563980074,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.45796258411224,
"count": 464382,
"is_parallel": true,
"self": 62.45796258411224
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 527.1435420459987,
"count": 232192,
"self": 7.045670322993601,
"children": {
"process_trajectory": {
"total": 136.4409142550062,
"count": 232192,
"self": 135.11660512600588,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3243091290003122,
"count": 10,
"self": 1.3243091290003122
}
}
},
"_update_policy": {
"total": 383.65695746799895,
"count": 97,
"self": 323.03555927601474,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.62139819198421,
"count": 2910,
"self": 60.62139819198421
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.870000212686136e-07,
"count": 1,
"self": 9.870000212686136e-07
},
"TrainerController._save_models": {
"total": 0.1254164420001871,
"count": 1,
"self": 0.001933594000092853,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12348284800009424,
"count": 1,
"self": 0.12348284800009424
}
}
}
}
}
}
}