ppo-Huggy / run_logs /timers.json
fashingabo's picture
Huggy
30a1e42 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.402122139930725,
"min": 1.402122139930725,
"max": 1.4279755353927612,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70745.4765625,
"min": 68052.7890625,
"max": 75617.125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 96.92745098039215,
"min": 86.81195079086116,
"max": 380.09090909090907,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49433.0,
"min": 49170.0,
"max": 50172.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999875.0,
"min": 49998.0,
"max": 1999875.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999875.0,
"min": 49998.0,
"max": 1999875.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3726279735565186,
"min": 0.0996384546160698,
"max": 2.4380853176116943,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1210.040283203125,
"min": 13.052637100219727,
"max": 1354.270263671875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.683812915577608,
"min": 1.822503227541465,
"max": 3.958117694718631,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1878.74458694458,
"min": 238.7479228079319,
"max": 2124.325817346573,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.683812915577608,
"min": 1.822503227541465,
"max": 3.958117694718631,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1878.74458694458,
"min": 238.7479228079319,
"max": 2124.325817346573,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014028858189218833,
"min": 0.014028858189218833,
"max": 0.020279964957201933,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0420865745676565,
"min": 0.02863184523157543,
"max": 0.05967159195436883,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0507203436560101,
"min": 0.022926930679629247,
"max": 0.06072185045729081,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1521610309680303,
"min": 0.045853861359258494,
"max": 0.1799243211746216,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3066988978000033e-06,
"min": 3.3066988978000033e-06,
"max": 0.00029533590155469996,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.92009669340001e-06,
"min": 9.92009669340001e-06,
"max": 0.00084421336859555,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10110219999999999,
"min": 0.10110219999999999,
"max": 0.1984453,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3033066,
"min": 0.20733290000000001,
"max": 0.58140445,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.499978000000007e-05,
"min": 6.499978000000007e-05,
"max": 0.004922420469999998,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019499934000000022,
"min": 0.00019499934000000022,
"max": 0.014072082055000004,
"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": "1721139901",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "1721142366"
},
"total": 2464.832695182,
"count": 1,
"self": 0.4372280600000522,
"children": {
"run_training.setup": {
"total": 0.08731318399998145,
"count": 1,
"self": 0.08731318399998145
},
"TrainerController.start_learning": {
"total": 2464.308153938,
"count": 1,
"self": 4.4717989398909594,
"children": {
"TrainerController._reset_env": {
"total": 3.321775756999955,
"count": 1,
"self": 3.321775756999955
},
"TrainerController.advance": {
"total": 2456.395627107109,
"count": 231657,
"self": 4.744436004988984,
"children": {
"env_step": {
"total": 1950.3289169570505,
"count": 231657,
"self": 1613.27285674418,
"children": {
"SubprocessEnvManager._take_step": {
"total": 334.09590472398213,
"count": 231657,
"self": 16.740130630952763,
"children": {
"TorchPolicy.evaluate": {
"total": 317.35577409302937,
"count": 222950,
"self": 317.35577409302937
}
}
},
"workers": {
"total": 2.9601554888885175,
"count": 231657,
"self": 0.0,
"children": {
"worker_root": {
"total": 2456.9650107209663,
"count": 231657,
"is_parallel": true,
"self": 1157.9896672389984,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001104576999978235,
"count": 1,
"is_parallel": true,
"self": 0.00032516900000700844,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007794079999712267,
"count": 2,
"is_parallel": true,
"self": 0.0007794079999712267
}
}
},
"UnityEnvironment.step": {
"total": 0.029792259000032573,
"count": 1,
"is_parallel": true,
"self": 0.00038221099998736463,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023689400006787764,
"count": 1,
"is_parallel": true,
"self": 0.00023689400006787764
},
"communicator.exchange": {
"total": 0.028422352999996292,
"count": 1,
"is_parallel": true,
"self": 0.028422352999996292
},
"steps_from_proto": {
"total": 0.0007508009999810383,
"count": 1,
"is_parallel": true,
"self": 0.00019604199997047544,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005547590000105629,
"count": 2,
"is_parallel": true,
"self": 0.0005547590000105629
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1298.975343481968,
"count": 231656,
"is_parallel": true,
"self": 39.587939944163054,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.62947773296798,
"count": 231656,
"is_parallel": true,
"self": 84.62947773296798
},
"communicator.exchange": {
"total": 1082.5554130219389,
"count": 231656,
"is_parallel": true,
"self": 1082.5554130219389
},
"steps_from_proto": {
"total": 92.20251278289777,
"count": 231656,
"is_parallel": true,
"self": 34.642395124048335,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.560117658849435,
"count": 463312,
"is_parallel": true,
"self": 57.560117658849435
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 501.3222741450693,
"count": 231657,
"self": 7.136791501012908,
"children": {
"process_trajectory": {
"total": 158.30783321505635,
"count": 231657,
"self": 157.050484865057,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2573483499993472,
"count": 10,
"self": 1.2573483499993472
}
}
},
"_update_policy": {
"total": 335.87764942900003,
"count": 97,
"self": 271.1963879010111,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.68126152798891,
"count": 2910,
"self": 64.68126152798891
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.25000222196104e-07,
"count": 1,
"self": 9.25000222196104e-07
},
"TrainerController._save_models": {
"total": 0.11895120899998801,
"count": 1,
"self": 0.0021356659999582916,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11681554300002972,
"count": 1,
"self": 0.11681554300002972
}
}
}
}
}
}
}