ppo-Huggy / run_logs /timers.json
hhubert's picture
Huggy
0ccbeea verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4069316387176514,
"min": 1.4069316387176514,
"max": 1.429613709449768,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70215.734375,
"min": 67724.1796875,
"max": 76159.921875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 84.0765306122449,
"min": 73.30312035661218,
"max": 381.08396946564886,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49437.0,
"min": 49186.0,
"max": 50062.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999985.0,
"min": 49303.0,
"max": 1999985.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999985.0,
"min": 49303.0,
"max": 1999985.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.423163652420044,
"min": 0.03173644840717316,
"max": 2.5191640853881836,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1424.8201904296875,
"min": 4.125738143920898,
"max": 1673.184326171875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.62681523370905,
"min": 1.691045256990653,
"max": 4.054255060037236,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2132.5673574209213,
"min": 219.83588340878487,
"max": 2655.520271360874,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.62681523370905,
"min": 1.691045256990653,
"max": 4.054255060037236,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2132.5673574209213,
"min": 219.83588340878487,
"max": 2655.520271360874,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01970561847135994,
"min": 0.01444173843807827,
"max": 0.020354065080270326,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.059116855414079815,
"min": 0.02888347687615654,
"max": 0.059116855414079815,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.053264408641391335,
"min": 0.023072048525015515,
"max": 0.06378308571875095,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.159793225924174,
"min": 0.04614409705003103,
"max": 0.19134925715625284,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.8248987250666724e-06,
"min": 3.8248987250666724e-06,
"max": 0.00029533875155375003,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1474696175200018e-05,
"min": 1.1474696175200018e-05,
"max": 0.0008440486686504499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10127493333333336,
"min": 0.10127493333333336,
"max": 0.19844625000000007,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30382480000000006,
"min": 0.20771825000000002,
"max": 0.5813495500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.361917333333345e-05,
"min": 7.361917333333345e-05,
"max": 0.004922467875000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022085752000000034,
"min": 0.00022085752000000034,
"max": 0.014069342544999999,
"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": "1719100530",
"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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1719103046"
},
"total": 2516.191492548,
"count": 1,
"self": 0.4449093060006817,
"children": {
"run_training.setup": {
"total": 0.05720528599999852,
"count": 1,
"self": 0.05720528599999852
},
"TrainerController.start_learning": {
"total": 2515.6893779559996,
"count": 1,
"self": 4.548950040973068,
"children": {
"TrainerController._reset_env": {
"total": 2.9337910090000605,
"count": 1,
"self": 2.9337910090000605
},
"TrainerController.advance": {
"total": 2508.0846123780266,
"count": 233129,
"self": 4.891304720015796,
"children": {
"env_step": {
"total": 1994.7140481870617,
"count": 233129,
"self": 1654.1637044361446,
"children": {
"SubprocessEnvManager._take_step": {
"total": 337.3681765919001,
"count": 233129,
"self": 17.541266768871424,
"children": {
"TorchPolicy.evaluate": {
"total": 319.8269098230287,
"count": 222982,
"self": 319.8269098230287
}
}
},
"workers": {
"total": 3.182167159016899,
"count": 233129,
"self": 0.0,
"children": {
"worker_root": {
"total": 2508.294791139094,
"count": 233129,
"is_parallel": true,
"self": 1179.503978657982,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000874334000059207,
"count": 1,
"is_parallel": true,
"self": 0.00022712999998475425,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006472040000744528,
"count": 2,
"is_parallel": true,
"self": 0.0006472040000744528
}
}
},
"UnityEnvironment.step": {
"total": 0.03063813599999321,
"count": 1,
"is_parallel": true,
"self": 0.00037354099993081036,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021359200002279977,
"count": 1,
"is_parallel": true,
"self": 0.00021359200002279977
},
"communicator.exchange": {
"total": 0.029308269000011933,
"count": 1,
"is_parallel": true,
"self": 0.029308269000011933
},
"steps_from_proto": {
"total": 0.0007427340000276672,
"count": 1,
"is_parallel": true,
"self": 0.00020753400008288736,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005351999999447798,
"count": 2,
"is_parallel": true,
"self": 0.0005351999999447798
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1328.7908124811117,
"count": 233128,
"is_parallel": true,
"self": 40.13935968220562,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.62785031594137,
"count": 233128,
"is_parallel": true,
"self": 85.62785031594137
},
"communicator.exchange": {
"total": 1108.8672668509296,
"count": 233128,
"is_parallel": true,
"self": 1108.8672668509296
},
"steps_from_proto": {
"total": 94.15633563203528,
"count": 233128,
"is_parallel": true,
"self": 35.687629845108404,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.468705786926876,
"count": 466256,
"is_parallel": true,
"self": 58.468705786926876
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 508.4792594709488,
"count": 233129,
"self": 7.086890255981871,
"children": {
"process_trajectory": {
"total": 167.00351974296495,
"count": 233129,
"self": 165.66705229396473,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3364674490002244,
"count": 10,
"self": 1.3364674490002244
}
}
},
"_update_policy": {
"total": 334.388849472002,
"count": 97,
"self": 270.5125204649895,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.87632900701249,
"count": 2910,
"self": 63.87632900701249
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.520000847056508e-07,
"count": 1,
"self": 8.520000847056508e-07
},
"TrainerController._save_models": {
"total": 0.12202367600002617,
"count": 1,
"self": 0.0017786439998417336,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12024503200018444,
"count": 1,
"self": 0.12024503200018444
}
}
}
}
}
}
}