ppo-Huggy / run_logs /timers.json
ArpitSinghGautam's picture
pushed Huggy
95002c3
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4085339307785034,
"min": 1.4085339307785034,
"max": 1.4321264028549194,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70859.1171875,
"min": 69088.71875,
"max": 76364.7109375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 95.31782945736434,
"min": 86.16230366492147,
"max": 373.47014925373134,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49184.0,
"min": 48959.0,
"max": 50191.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999953.0,
"min": 49552.0,
"max": 1999953.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999953.0,
"min": 49552.0,
"max": 1999953.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4149558544158936,
"min": 0.15302978456020355,
"max": 2.4996578693389893,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1246.1171875,
"min": 20.35296058654785,
"max": 1350.3114013671875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.738774903060854,
"min": 1.7613048080663036,
"max": 3.907495610941024,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1929.2078499794006,
"min": 234.25353947281837,
"max": 2095.5933645367622,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.738774903060854,
"min": 1.7613048080663036,
"max": 3.907495610941024,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1929.2078499794006,
"min": 234.25353947281837,
"max": 2095.5933645367622,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.02036733741600377,
"min": 0.01371628546815676,
"max": 0.020903485397381398,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04073467483200754,
"min": 0.02743257093631352,
"max": 0.05796088986147273,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.054546992853283884,
"min": 0.021900547792514165,
"max": 0.06089662123057577,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10909398570656777,
"min": 0.04380109558502833,
"max": 0.18268986369172732,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.617773460774998e-06,
"min": 4.617773460774998e-06,
"max": 0.0002953509015496999,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.235546921549996e-06,
"min": 9.235546921549996e-06,
"max": 0.0008441863686045499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10153922500000001,
"min": 0.10153922500000001,
"max": 0.19845030000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20307845000000002,
"min": 0.20307845000000002,
"max": 0.5813954499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.680732749999998e-05,
"min": 8.680732749999998e-05,
"max": 0.004922669970000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017361465499999995,
"min": 0.00017361465499999995,
"max": 0.014071632955,
"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": "1704023801",
"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=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1704026192"
},
"total": 2390.9407553110004,
"count": 1,
"self": 0.6496715060002316,
"children": {
"run_training.setup": {
"total": 0.06202563699997654,
"count": 1,
"self": 0.06202563699997654
},
"TrainerController.start_learning": {
"total": 2390.2290581680004,
"count": 1,
"self": 4.495568468932106,
"children": {
"TrainerController._reset_env": {
"total": 3.0286270249999916,
"count": 1,
"self": 3.0286270249999916
},
"TrainerController.advance": {
"total": 2382.536335128069,
"count": 231881,
"self": 4.596342081040802,
"children": {
"env_step": {
"total": 1896.1823430140842,
"count": 231881,
"self": 1574.9170731300674,
"children": {
"SubprocessEnvManager._take_step": {
"total": 318.4489010120476,
"count": 231881,
"self": 16.913599679117112,
"children": {
"TorchPolicy.evaluate": {
"total": 301.5353013329305,
"count": 222942,
"self": 301.5353013329305
}
}
},
"workers": {
"total": 2.816368871969189,
"count": 231881,
"self": 0.0,
"children": {
"worker_root": {
"total": 2382.903730026082,
"count": 231881,
"is_parallel": true,
"self": 1104.3962618709882,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0006275780000351006,
"count": 1,
"is_parallel": true,
"self": 0.00019101699996326715,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004365610000718334,
"count": 2,
"is_parallel": true,
"self": 0.0004365610000718334
}
}
},
"UnityEnvironment.step": {
"total": 0.03266382699996484,
"count": 1,
"is_parallel": true,
"self": 0.0003085580000288246,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001895239999498699,
"count": 1,
"is_parallel": true,
"self": 0.0001895239999498699
},
"communicator.exchange": {
"total": 0.03145461699995167,
"count": 1,
"is_parallel": true,
"self": 0.03145461699995167
},
"steps_from_proto": {
"total": 0.0007111280000344777,
"count": 1,
"is_parallel": true,
"self": 0.00019093400004521754,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005201939999892602,
"count": 2,
"is_parallel": true,
"self": 0.0005201939999892602
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1278.5074681550939,
"count": 231880,
"is_parallel": true,
"self": 40.1445351430948,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.63667084609682,
"count": 231880,
"is_parallel": true,
"self": 82.63667084609682
},
"communicator.exchange": {
"total": 1067.1391071320054,
"count": 231880,
"is_parallel": true,
"self": 1067.1391071320054
},
"steps_from_proto": {
"total": 88.5871550338968,
"count": 231880,
"is_parallel": true,
"self": 31.046717716724118,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.54043731717269,
"count": 463760,
"is_parallel": true,
"self": 57.54043731717269
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 481.75765003294373,
"count": 231881,
"self": 6.946752797884756,
"children": {
"process_trajectory": {
"total": 149.68959188306002,
"count": 231881,
"self": 148.35247316906072,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3371187139993026,
"count": 10,
"self": 1.3371187139993026
}
}
},
"_update_policy": {
"total": 325.12130535199896,
"count": 96,
"self": 261.6471294130023,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.474175938996666,
"count": 2880,
"self": 63.474175938996666
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2429995877027977e-06,
"count": 1,
"self": 1.2429995877027977e-06
},
"TrainerController._save_models": {
"total": 0.16852630299990778,
"count": 1,
"self": 0.0027855499997713196,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16574075300013646,
"count": 1,
"self": 0.16574075300013646
}
}
}
}
}
}
}