ppo-Huggy / run_logs /timers.json
JSlin's picture
Huggy
0275298 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4018992185592651,
"min": 1.4018992185592651,
"max": 1.4257357120513916,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70172.0625,
"min": 69140.4375,
"max": 78229.15625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 77.34639498432603,
"min": 69.21067415730337,
"max": 407.1532258064516,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49347.0,
"min": 49234.0,
"max": 50487.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999982.0,
"min": 49861.0,
"max": 1999982.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999982.0,
"min": 49861.0,
"max": 1999982.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.507601737976074,
"min": 0.1012519896030426,
"max": 2.5352654457092285,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1599.849853515625,
"min": 12.453994750976562,
"max": 1772.336669921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.811634164151727,
"min": 1.9735263243196457,
"max": 4.051459196439824,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2431.8225967288017,
"min": 242.7437378913164,
"max": 2828.1758151054382,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.811634164151727,
"min": 1.9735263243196457,
"max": 4.051459196439824,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2431.8225967288017,
"min": 242.7437378913164,
"max": 2828.1758151054382,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015319510742887765,
"min": 0.013900438697252562,
"max": 0.01945039353674171,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04595853222866329,
"min": 0.027800877394505125,
"max": 0.05770827373350282,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05721796779996819,
"min": 0.022221934578071038,
"max": 0.0591950369377931,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17165390339990458,
"min": 0.044443869156142075,
"max": 0.1740615504483382,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.8014487328833362e-06,
"min": 3.8014487328833362e-06,
"max": 0.00029535727654757493,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1404346198650008e-05,
"min": 1.1404346198650008e-05,
"max": 0.00084396526867825,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10126711666666667,
"min": 0.10126711666666667,
"max": 0.19845242500000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30380135,
"min": 0.20767374999999993,
"max": 0.58132175,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.322912166666673e-05,
"min": 7.322912166666673e-05,
"max": 0.004922776007499998,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021968736500000018,
"min": 0.00021968736500000018,
"max": 0.014067955325000004,
"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": "1744632016",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics --torch-device=cuda:0",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1744634540"
},
"total": 2523.598301604,
"count": 1,
"self": 0.436201088999951,
"children": {
"run_training.setup": {
"total": 0.028963660999977492,
"count": 1,
"self": 0.028963660999977492
},
"TrainerController.start_learning": {
"total": 2523.133136854,
"count": 1,
"self": 4.647136289006994,
"children": {
"TrainerController._reset_env": {
"total": 3.265813546000004,
"count": 1,
"self": 3.265813546000004
},
"TrainerController.advance": {
"total": 2515.0998468519924,
"count": 233691,
"self": 4.7526307561252,
"children": {
"env_step": {
"total": 2018.4827605419266,
"count": 233691,
"self": 1586.2943251190375,
"children": {
"SubprocessEnvManager._take_step": {
"total": 429.4085281209417,
"count": 233691,
"self": 16.974925842019957,
"children": {
"TorchPolicy.evaluate": {
"total": 412.43360227892174,
"count": 222970,
"self": 412.43360227892174
}
}
},
"workers": {
"total": 2.7799073019473894,
"count": 233691,
"self": 0.0,
"children": {
"worker_root": {
"total": 2515.5994230419014,
"count": 233691,
"is_parallel": true,
"self": 1222.3476265398756,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010604280000166,
"count": 1,
"is_parallel": true,
"self": 0.0003887809999696401,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006716470000469599,
"count": 2,
"is_parallel": true,
"self": 0.0006716470000469599
}
}
},
"UnityEnvironment.step": {
"total": 0.05665705000001253,
"count": 1,
"is_parallel": true,
"self": 0.0003520870000670584,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020173399997247543,
"count": 1,
"is_parallel": true,
"self": 0.00020173399997247543
},
"communicator.exchange": {
"total": 0.05535551499997382,
"count": 1,
"is_parallel": true,
"self": 0.05535551499997382
},
"steps_from_proto": {
"total": 0.0007477139999991778,
"count": 1,
"is_parallel": true,
"self": 0.00019931299999598195,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005484010000031958,
"count": 2,
"is_parallel": true,
"self": 0.0005484010000031958
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1293.2517965020259,
"count": 233690,
"is_parallel": true,
"self": 38.54736494207373,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.44969202598537,
"count": 233690,
"is_parallel": true,
"self": 84.44969202598537
},
"communicator.exchange": {
"total": 1080.521323679965,
"count": 233690,
"is_parallel": true,
"self": 1080.521323679965
},
"steps_from_proto": {
"total": 89.73341585400186,
"count": 233690,
"is_parallel": true,
"self": 33.60734938601803,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.12606646798383,
"count": 467380,
"is_parallel": true,
"self": 56.12606646798383
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 491.86445555394056,
"count": 233691,
"self": 6.9931141928606735,
"children": {
"process_trajectory": {
"total": 176.55955316707735,
"count": 233691,
"self": 175.07654008907792,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4830130779994306,
"count": 10,
"self": 1.4830130779994306
}
}
},
"_update_policy": {
"total": 308.31178819400253,
"count": 97,
"self": 244.48728398700018,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.82450420700235,
"count": 2910,
"self": 63.82450420700235
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.600001481478103e-07,
"count": 1,
"self": 7.600001481478103e-07
},
"TrainerController._save_models": {
"total": 0.12033940700030143,
"count": 1,
"self": 0.0019065180003963178,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11843288899990512,
"count": 1,
"self": 0.11843288899990512
}
}
}
}
}
}
}