ppo-Pyramind / run_logs /timers.json
rishipatel92's picture
First Push of Pyramid
1166bba
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3881414532661438,
"min": 0.3881414532661438,
"max": 1.4327198266983032,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11712.556640625,
"min": 11712.556640625,
"max": 43462.98828125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989954.0,
"min": 29992.0,
"max": 989954.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989954.0,
"min": 29992.0,
"max": 989954.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.49166133999824524,
"min": -0.09401962161064148,
"max": 0.5447959303855896,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 132.74856567382812,
"min": -22.84676742553711,
"max": 148.7292938232422,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.038425181061029434,
"min": -0.0548870824277401,
"max": 0.36479705572128296,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 10.374798774719238,
"min": -14.160867691040039,
"max": 86.82170104980469,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06955204964227353,
"min": 0.06401743788904111,
"max": 0.0715762134932925,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.043280744634103,
"min": 0.5010334944530476,
"max": 1.0558608176195812,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015147672304172171,
"min": 0.0011067138484128285,
"max": 0.01730428183024439,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22721508456258258,
"min": 0.014741411831642194,
"max": 0.24225994562342143,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.502657499146669e-06,
"min": 7.502657499146669e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011253986248720004,
"min": 0.00011253986248720004,
"max": 0.0038828428057190996,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10250085333333335,
"min": 0.10250085333333335,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5375128000000002,
"min": 1.3886848,
"max": 2.6942809,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025983524800000013,
"min": 0.00025983524800000013,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0038975287200000023,
"min": 0.0038975287200000023,
"max": 0.12943866191,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.012800367549061775,
"min": 0.01263515092432499,
"max": 0.5057960152626038,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.19200551509857178,
"min": 0.17689211666584015,
"max": 3.540571928024292,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 388.875,
"min": 335.8636363636364,
"max": 987.7058823529412,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 27999.0,
"min": 16791.0,
"max": 32928.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5363305395262108,
"min": -0.8710000462391797,
"max": 1.6151011325847144,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 110.61579884588718,
"min": -28.303401619195938,
"max": 140.51379853487015,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5363305395262108,
"min": -0.8710000462391797,
"max": 1.6151011325847144,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 110.61579884588718,
"min": -28.303401619195938,
"max": 140.51379853487015,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.05094729104914424,
"min": 0.047022295033896405,
"max": 9.956047527930316,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.6682049555383855,
"min": 3.6682049555383855,
"max": 169.25280797481537,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1673379635",
"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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1673381799"
},
"total": 2163.8649115730004,
"count": 1,
"self": 0.4255620390003969,
"children": {
"run_training.setup": {
"total": 0.1073837989997628,
"count": 1,
"self": 0.1073837989997628
},
"TrainerController.start_learning": {
"total": 2163.3319657350003,
"count": 1,
"self": 1.3916125209907477,
"children": {
"TrainerController._reset_env": {
"total": 6.584981768000034,
"count": 1,
"self": 6.584981768000034
},
"TrainerController.advance": {
"total": 2155.26118515501,
"count": 63816,
"self": 1.3465345400391016,
"children": {
"env_step": {
"total": 1445.4846057460454,
"count": 63816,
"self": 1335.3716316628233,
"children": {
"SubprocessEnvManager._take_step": {
"total": 109.27467821219216,
"count": 63816,
"self": 4.380260380187792,
"children": {
"TorchPolicy.evaluate": {
"total": 104.89441783200436,
"count": 62581,
"self": 35.281439506142306,
"children": {
"TorchPolicy.sample_actions": {
"total": 69.61297832586206,
"count": 62581,
"self": 69.61297832586206
}
}
}
}
},
"workers": {
"total": 0.8382958710299135,
"count": 63816,
"self": 0.0,
"children": {
"worker_root": {
"total": 2158.4899822958514,
"count": 63816,
"is_parallel": true,
"self": 929.4893882487104,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001828830000704329,
"count": 1,
"is_parallel": true,
"self": 0.000655786000606895,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001173044000097434,
"count": 8,
"is_parallel": true,
"self": 0.001173044000097434
}
}
},
"UnityEnvironment.step": {
"total": 0.04375481300030515,
"count": 1,
"is_parallel": true,
"self": 0.00048751199938124046,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042577400017762557,
"count": 1,
"is_parallel": true,
"self": 0.00042577400017762557
},
"communicator.exchange": {
"total": 0.04123810200053413,
"count": 1,
"is_parallel": true,
"self": 0.04123810200053413
},
"steps_from_proto": {
"total": 0.0016034250002121553,
"count": 1,
"is_parallel": true,
"self": 0.00046190599914552877,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011415190010666265,
"count": 8,
"is_parallel": true,
"self": 0.0011415190010666265
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1229.000594047141,
"count": 63815,
"is_parallel": true,
"self": 29.517216351174284,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.42530785888539,
"count": 63815,
"is_parallel": true,
"self": 23.42530785888539
},
"communicator.exchange": {
"total": 1069.5178389330677,
"count": 63815,
"is_parallel": true,
"self": 1069.5178389330677
},
"steps_from_proto": {
"total": 106.5402309040137,
"count": 63815,
"is_parallel": true,
"self": 23.638507169009245,
"children": {
"_process_rank_one_or_two_observation": {
"total": 82.90172373500445,
"count": 510520,
"is_parallel": true,
"self": 82.90172373500445
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 708.4300448689255,
"count": 63816,
"self": 2.6112820278749496,
"children": {
"process_trajectory": {
"total": 155.33752311803983,
"count": 63816,
"self": 155.1386373860405,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1988857319993258,
"count": 2,
"self": 0.1988857319993258
}
}
},
"_update_policy": {
"total": 550.4812397230107,
"count": 456,
"self": 213.38282488001005,
"children": {
"TorchPPOOptimizer.update": {
"total": 337.0984148430007,
"count": 22755,
"self": 337.0984148430007
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.979995982372202e-07,
"count": 1,
"self": 8.979995982372202e-07
},
"TrainerController._save_models": {
"total": 0.0941853929998615,
"count": 1,
"self": 0.00139259800016589,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09279279499969562,
"count": 1,
"self": 0.09279279499969562
}
}
}
}
}
}
}