ppo-Huggy / run_logs /timers.json
tsfeith's picture
Huggy
f3d0e14 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.408267617225647,
"min": 1.408267617225647,
"max": 1.428063154220581,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69469.84375,
"min": 68422.9296875,
"max": 79173.6484375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 84.38421955403088,
"min": 82.45075125208682,
"max": 376.50375939849624,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49196.0,
"min": 48996.0,
"max": 50075.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999985.0,
"min": 49985.0,
"max": 1999985.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999985.0,
"min": 49985.0,
"max": 1999985.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4750964641571045,
"min": 0.16816286742687225,
"max": 2.493500232696533,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1442.981201171875,
"min": 22.197498321533203,
"max": 1455.6680908203125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.805398813447249,
"min": 1.770644206215035,
"max": 3.918078849098899,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2218.547508239746,
"min": 233.7250352203846,
"max": 2252.281223475933,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.805398813447249,
"min": 1.770644206215035,
"max": 3.918078849098899,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2218.547508239746,
"min": 233.7250352203846,
"max": 2252.281223475933,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014764921004744894,
"min": 0.013158056811870563,
"max": 0.020102095876063687,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.044294763014234684,
"min": 0.02882076232538869,
"max": 0.05451210971999293,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05789551109903388,
"min": 0.020411111880093813,
"max": 0.06603887192904949,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17368653329710165,
"min": 0.040822223760187626,
"max": 0.18406596047182877,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2675489108499953e-06,
"min": 3.2675489108499953e-06,
"max": 0.00029528145157284996,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.802646732549986e-06,
"min": 9.802646732549986e-06,
"max": 0.0008439561186812997,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10108915000000003,
"min": 0.10108915000000003,
"max": 0.19842715000000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3032674500000001,
"min": 0.20734949999999996,
"max": 0.5813187,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.434858499999989e-05,
"min": 6.434858499999989e-05,
"max": 0.004921514785000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019304575499999967,
"min": 0.00019304575499999967,
"max": 0.01406780313,
"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": "1709044010",
"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": "1709046369"
},
"total": 2359.424224029,
"count": 1,
"self": 0.39802813599999354,
"children": {
"run_training.setup": {
"total": 0.05231289200003175,
"count": 1,
"self": 0.05231289200003175
},
"TrainerController.start_learning": {
"total": 2358.973883001,
"count": 1,
"self": 4.28054787810197,
"children": {
"TrainerController._reset_env": {
"total": 3.6300931050000145,
"count": 1,
"self": 3.6300931050000145
},
"TrainerController.advance": {
"total": 2350.9468435128983,
"count": 232541,
"self": 4.631487373963864,
"children": {
"env_step": {
"total": 1871.671656119975,
"count": 232541,
"self": 1545.1948391081016,
"children": {
"SubprocessEnvManager._take_step": {
"total": 323.7200052019922,
"count": 232541,
"self": 16.180317254960073,
"children": {
"TorchPolicy.evaluate": {
"total": 307.5396879470321,
"count": 222908,
"self": 307.5396879470321
}
}
},
"workers": {
"total": 2.756811809881242,
"count": 232541,
"self": 0.0,
"children": {
"worker_root": {
"total": 2351.6672232529054,
"count": 232541,
"is_parallel": true,
"self": 1095.2005747518638,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009418900000355279,
"count": 1,
"is_parallel": true,
"self": 0.00025883800014980807,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006830519998857199,
"count": 2,
"is_parallel": true,
"self": 0.0006830519998857199
}
}
},
"UnityEnvironment.step": {
"total": 0.02942235700004403,
"count": 1,
"is_parallel": true,
"self": 0.0003624040000431705,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021647500000199216,
"count": 1,
"is_parallel": true,
"self": 0.00021647500000199216
},
"communicator.exchange": {
"total": 0.02811295499998323,
"count": 1,
"is_parallel": true,
"self": 0.02811295499998323
},
"steps_from_proto": {
"total": 0.0007305230000156371,
"count": 1,
"is_parallel": true,
"self": 0.00020220199996856536,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005283210000470717,
"count": 2,
"is_parallel": true,
"self": 0.0005283210000470717
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1256.4666485010416,
"count": 232540,
"is_parallel": true,
"self": 41.02576268584721,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.44035086509007,
"count": 232540,
"is_parallel": true,
"self": 84.44035086509007
},
"communicator.exchange": {
"total": 1039.2606405690149,
"count": 232540,
"is_parallel": true,
"self": 1039.2606405690149
},
"steps_from_proto": {
"total": 91.73989438108947,
"count": 232540,
"is_parallel": true,
"self": 33.858149315050696,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.881745066038775,
"count": 465080,
"is_parallel": true,
"self": 57.881745066038775
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 474.64370001895963,
"count": 232541,
"self": 6.445654164883194,
"children": {
"process_trajectory": {
"total": 149.8762813740775,
"count": 232541,
"self": 148.6780690410776,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1982123329999013,
"count": 10,
"self": 1.1982123329999013
}
}
},
"_update_policy": {
"total": 318.32176447999893,
"count": 97,
"self": 255.22281528799272,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.098949192006216,
"count": 2910,
"self": 63.098949192006216
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0409999049443286e-06,
"count": 1,
"self": 1.0409999049443286e-06
},
"TrainerController._save_models": {
"total": 0.11639746399987416,
"count": 1,
"self": 0.0018943630002468126,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11450310099962735,
"count": 1,
"self": 0.11450310099962735
}
}
}
}
}
}
}