ppo-Huggy / run_logs /timers.json
sd99's picture
Push PPO-Huggy model
b66fe9f
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4057402610778809,
"min": 1.4057402610778809,
"max": 1.42774498462677,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69117.4375,
"min": 69117.4375,
"max": 75634.7421875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 85.61698440207972,
"min": 70.88505747126437,
"max": 388.984496124031,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49401.0,
"min": 49006.0,
"max": 50179.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999976.0,
"min": 49911.0,
"max": 1999976.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999976.0,
"min": 49911.0,
"max": 1999976.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4992682933807373,
"min": 0.15530210733413696,
"max": 2.5232832431793213,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1442.0777587890625,
"min": 19.87866973876953,
"max": 1689.544189453125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.874966086506637,
"min": 1.8676997101865709,
"max": 4.036282603268151,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2235.8554319143295,
"min": 239.06556290388107,
"max": 2702.847842514515,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.874966086506637,
"min": 1.8676997101865709,
"max": 4.036282603268151,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2235.8554319143295,
"min": 239.06556290388107,
"max": 2702.847842514515,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01655521359643899,
"min": 0.013114593829474568,
"max": 0.020926605859131087,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04966564078931697,
"min": 0.026229187658949136,
"max": 0.054989766520156996,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05214286355508698,
"min": 0.021271683741360903,
"max": 0.06552438922226429,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15642859066526094,
"min": 0.042543367482721806,
"max": 0.18165501790742078,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4877988374333283e-06,
"min": 3.4877988374333283e-06,
"max": 0.0002952732765755749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0463396512299985e-05,
"min": 1.0463396512299985e-05,
"max": 0.0008437921687359498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10116256666666666,
"min": 0.10116256666666666,
"max": 0.19842442500000007,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30348769999999997,
"min": 0.20746824999999997,
"max": 0.5812640499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.801207666666657e-05,
"min": 6.801207666666657e-05,
"max": 0.004921378807500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002040362299999997,
"min": 0.0002040362299999997,
"max": 0.014065076095000002,
"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": "1673076159",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1673078440"
},
"total": 2280.706388642,
"count": 1,
"self": 0.39428420100011863,
"children": {
"run_training.setup": {
"total": 0.1051854289999028,
"count": 1,
"self": 0.1051854289999028
},
"TrainerController.start_learning": {
"total": 2280.206919012,
"count": 1,
"self": 4.139219990028323,
"children": {
"TrainerController._reset_env": {
"total": 7.419387810999979,
"count": 1,
"self": 7.419387810999979
},
"TrainerController.advance": {
"total": 2268.5366655709713,
"count": 233360,
"self": 4.080514177975601,
"children": {
"env_step": {
"total": 1788.0311045179828,
"count": 233360,
"self": 1504.1885081709702,
"children": {
"SubprocessEnvManager._take_step": {
"total": 281.0979636569905,
"count": 233360,
"self": 14.783668700091539,
"children": {
"TorchPolicy.evaluate": {
"total": 266.31429495689895,
"count": 222941,
"self": 66.29416969086674,
"children": {
"TorchPolicy.sample_actions": {
"total": 200.0201252660322,
"count": 222941,
"self": 200.0201252660322
}
}
}
}
},
"workers": {
"total": 2.744632690022172,
"count": 233360,
"self": 0.0,
"children": {
"worker_root": {
"total": 2272.0898559889047,
"count": 233360,
"is_parallel": true,
"self": 1033.1640548647767,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004809702999864385,
"count": 1,
"is_parallel": true,
"self": 0.0005136629995377007,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004296040000326684,
"count": 2,
"is_parallel": true,
"self": 0.004296040000326684
}
}
},
"UnityEnvironment.step": {
"total": 0.027492973000107668,
"count": 1,
"is_parallel": true,
"self": 0.00029022300032011117,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00017313099988314207,
"count": 1,
"is_parallel": true,
"self": 0.00017313099988314207
},
"communicator.exchange": {
"total": 0.026280751000058444,
"count": 1,
"is_parallel": true,
"self": 0.026280751000058444
},
"steps_from_proto": {
"total": 0.0007488679998459702,
"count": 1,
"is_parallel": true,
"self": 0.0002743919999375066,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00047447599990846356,
"count": 2,
"is_parallel": true,
"self": 0.00047447599990846356
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1238.925801124128,
"count": 233359,
"is_parallel": true,
"self": 34.87730801618636,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.71562894788394,
"count": 233359,
"is_parallel": true,
"self": 79.71562894788394
},
"communicator.exchange": {
"total": 1026.8785472359998,
"count": 233359,
"is_parallel": true,
"self": 1026.8785472359998
},
"steps_from_proto": {
"total": 97.45431692405782,
"count": 233359,
"is_parallel": true,
"self": 42.35533545904582,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.098981465012,
"count": 466718,
"is_parallel": true,
"self": 55.098981465012
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 476.42504687501287,
"count": 233360,
"self": 6.510647014866436,
"children": {
"process_trajectory": {
"total": 159.93633561414845,
"count": 233360,
"self": 158.78694423714774,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1493913770007111,
"count": 10,
"self": 1.1493913770007111
}
}
},
"_update_policy": {
"total": 309.978064245998,
"count": 97,
"self": 257.3177688730127,
"children": {
"TorchPPOOptimizer.update": {
"total": 52.660295372985274,
"count": 2910,
"self": 52.660295372985274
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2710002010862809e-06,
"count": 1,
"self": 1.2710002010862809e-06
},
"TrainerController._save_models": {
"total": 0.11164436900025976,
"count": 1,
"self": 0.0018811970003298484,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10976317199992991,
"count": 1,
"self": 0.10976317199992991
}
}
}
}
}
}
}