ppo-Huggy / run_logs /timers.json
wayandadang's picture
Huggy
b5a99c7 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4109506607055664,
"min": 1.4109506607055664,
"max": 1.4293241500854492,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70563.0546875,
"min": 67542.203125,
"max": 78221.078125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 77.94944707740916,
"min": 72.37298091042584,
"max": 417.775,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49342.0,
"min": 49201.0,
"max": 50281.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999946.0,
"min": 49874.0,
"max": 1999946.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999946.0,
"min": 49874.0,
"max": 1999946.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.487381935119629,
"min": 0.06487599015235901,
"max": 2.5409767627716064,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1574.5128173828125,
"min": 7.720242977142334,
"max": 1637.66162109375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.976125949649449,
"min": 1.7943220298831202,
"max": 4.069420482335466,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2516.8877261281013,
"min": 213.5243215560913,
"max": 2617.4802392721176,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.976125949649449,
"min": 1.7943220298831202,
"max": 4.069420482335466,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2516.8877261281013,
"min": 213.5243215560913,
"max": 2617.4802392721176,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017657726353111986,
"min": 0.01426416427930235,
"max": 0.022140697480062956,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05297317905933596,
"min": 0.0285283285586047,
"max": 0.05659202007615628,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.060954178911116395,
"min": 0.022263693840553364,
"max": 0.0629556081775162,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18286253673334918,
"min": 0.04452738768110673,
"max": 0.1888668245325486,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.645248784949997e-06,
"min": 3.645248784949997e-06,
"max": 0.00029525197658267503,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0935746354849991e-05,
"min": 1.0935746354849991e-05,
"max": 0.0008436609187796997,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10121504999999999,
"min": 0.10121504999999999,
"max": 0.19841732499999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30364515,
"min": 0.20756149999999995,
"max": 0.5812203,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.063099499999996e-05,
"min": 7.063099499999996e-05,
"max": 0.004921024517499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002118929849999999,
"min": 0.0002118929849999999,
"max": 0.014062892970000001,
"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": "1711421428",
"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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1711426453"
},
"total": 5025.494294904,
"count": 1,
"self": 0.6967257500000414,
"children": {
"run_training.setup": {
"total": 0.07135015899996233,
"count": 1,
"self": 0.07135015899996233
},
"TrainerController.start_learning": {
"total": 5024.726218995,
"count": 1,
"self": 9.168823193075696,
"children": {
"TrainerController._reset_env": {
"total": 3.716201960000035,
"count": 1,
"self": 3.716201960000035
},
"TrainerController.advance": {
"total": 5011.693234704924,
"count": 232845,
"self": 8.989310867750646,
"children": {
"env_step": {
"total": 3230.1592178821434,
"count": 232845,
"self": 2693.323031043036,
"children": {
"SubprocessEnvManager._take_step": {
"total": 530.5365600371339,
"count": 232845,
"self": 36.30059479427575,
"children": {
"TorchPolicy.evaluate": {
"total": 494.23596524285813,
"count": 222887,
"self": 494.23596524285813
}
}
},
"workers": {
"total": 6.299626801973773,
"count": 232845,
"self": 0.0,
"children": {
"worker_root": {
"total": 5009.558388332145,
"count": 232845,
"is_parallel": true,
"self": 2880.5048715330904,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010714009999901464,
"count": 1,
"is_parallel": true,
"self": 0.00025880199984840146,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008125990001417449,
"count": 2,
"is_parallel": true,
"self": 0.0008125990001417449
}
}
},
"UnityEnvironment.step": {
"total": 0.037987307999969744,
"count": 1,
"is_parallel": true,
"self": 0.0004930129998683697,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002495510000244394,
"count": 1,
"is_parallel": true,
"self": 0.0002495510000244394
},
"communicator.exchange": {
"total": 0.03628741500006072,
"count": 1,
"is_parallel": true,
"self": 0.03628741500006072
},
"steps_from_proto": {
"total": 0.000957329000016216,
"count": 1,
"is_parallel": true,
"self": 0.00026148899996769615,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006958400000485199,
"count": 2,
"is_parallel": true,
"self": 0.0006958400000485199
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2129.0535167990547,
"count": 232844,
"is_parallel": true,
"self": 65.03004862796206,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 98.28924863819555,
"count": 232844,
"is_parallel": true,
"self": 98.28924863819555
},
"communicator.exchange": {
"total": 1818.2416902889972,
"count": 232844,
"is_parallel": true,
"self": 1818.2416902889972
},
"steps_from_proto": {
"total": 147.49252924389975,
"count": 232844,
"is_parallel": true,
"self": 45.71036339505645,
"children": {
"_process_rank_one_or_two_observation": {
"total": 101.7821658488433,
"count": 465688,
"is_parallel": true,
"self": 101.7821658488433
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1772.5447059550302,
"count": 232845,
"self": 15.364760650014432,
"children": {
"process_trajectory": {
"total": 284.391981060017,
"count": 232845,
"self": 282.9606673870161,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4313136730008864,
"count": 10,
"self": 1.4313136730008864
}
}
},
"_update_policy": {
"total": 1472.7879642449989,
"count": 97,
"self": 358.5234622759781,
"children": {
"TorchPPOOptimizer.update": {
"total": 1114.2645019690208,
"count": 2910,
"self": 1114.2645019690208
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.719998731976375e-07,
"count": 1,
"self": 8.719998731976375e-07
},
"TrainerController._save_models": {
"total": 0.1479582649999429,
"count": 1,
"self": 0.0073435020003671525,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14061476299957576,
"count": 1,
"self": 0.14061476299957576
}
}
}
}
}
}
}