ppo-Huggy / run_logs /timers.json
hackvermin's picture
Huggy
c3765d0 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4110596179962158,
"min": 1.4110596179962158,
"max": 1.4318175315856934,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70661.6328125,
"min": 69429.515625,
"max": 78498.46875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 82.81742043551088,
"min": 76.02773497688752,
"max": 423.58474576271186,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49442.0,
"min": 48991.0,
"max": 50392.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999942.0,
"min": 49445.0,
"max": 1999942.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999942.0,
"min": 49445.0,
"max": 1999942.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4707493782043457,
"min": 0.13960599899291992,
"max": 2.5033233165740967,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1475.037353515625,
"min": 16.33390235900879,
"max": 1575.9293212890625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8333333568956385,
"min": 1.9671082677494767,
"max": 3.957498848438263,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2288.500014066696,
"min": 230.15166732668877,
"max": 2480.858733355999,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8333333568956385,
"min": 1.9671082677494767,
"max": 3.957498848438263,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2288.500014066696,
"min": 230.15166732668877,
"max": 2480.858733355999,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01768922799641991,
"min": 0.013626803898538735,
"max": 0.021813131719439598,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.053067683989259734,
"min": 0.02725360779707747,
"max": 0.05778938723318182,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05563412035504977,
"min": 0.020191977949192128,
"max": 0.07082414937516053,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1669023610651493,
"min": 0.040383955898384255,
"max": 0.2124724481254816,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.962498679200001e-06,
"min": 3.962498679200001e-06,
"max": 0.00029533725155424993,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1887496037600003e-05,
"min": 1.1887496037600003e-05,
"max": 0.0008442718685760498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1013208,
"min": 0.1013208,
"max": 0.1984457500000001,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3039624,
"min": 0.20776959999999997,
"max": 0.5814239499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.590791999999999e-05,
"min": 7.590791999999999e-05,
"max": 0.004922442924999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022772375999999996,
"min": 0.00022772375999999996,
"max": 0.014073055105000001,
"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": "1759240435",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1759242985"
},
"total": 2550.484685937,
"count": 1,
"self": 0.4548769170005471,
"children": {
"run_training.setup": {
"total": 0.037249883999948,
"count": 1,
"self": 0.037249883999948
},
"TrainerController.start_learning": {
"total": 2549.9925591359997,
"count": 1,
"self": 4.3637206261146275,
"children": {
"TrainerController._reset_env": {
"total": 3.387541646000045,
"count": 1,
"self": 3.387541646000045
},
"TrainerController.advance": {
"total": 2542.1431344778853,
"count": 232632,
"self": 4.357068618164703,
"children": {
"env_step": {
"total": 2072.6998165637733,
"count": 232632,
"self": 1668.7852533528041,
"children": {
"SubprocessEnvManager._take_step": {
"total": 401.05750009192684,
"count": 232632,
"self": 15.753812542018522,
"children": {
"TorchPolicy.evaluate": {
"total": 385.3036875499083,
"count": 222949,
"self": 385.3036875499083
}
}
},
"workers": {
"total": 2.857063119042323,
"count": 232632,
"self": 0.0,
"children": {
"worker_root": {
"total": 2537.7376260372184,
"count": 232632,
"is_parallel": true,
"self": 1182.3734788511767,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001114060999952926,
"count": 1,
"is_parallel": true,
"self": 0.0003201679999165208,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007938930000364053,
"count": 2,
"is_parallel": true,
"self": 0.0007938930000364053
}
}
},
"UnityEnvironment.step": {
"total": 0.028686880999885034,
"count": 1,
"is_parallel": true,
"self": 0.00033911699983946164,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001934550000441959,
"count": 1,
"is_parallel": true,
"self": 0.0001934550000441959
},
"communicator.exchange": {
"total": 0.02739717200006453,
"count": 1,
"is_parallel": true,
"self": 0.02739717200006453
},
"steps_from_proto": {
"total": 0.0007571369999368471,
"count": 1,
"is_parallel": true,
"self": 0.0001917029999276565,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005654340000091906,
"count": 2,
"is_parallel": true,
"self": 0.0005654340000091906
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1355.3641471860417,
"count": 232631,
"is_parallel": true,
"self": 37.40805450804169,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.74190575797365,
"count": 232631,
"is_parallel": true,
"self": 79.74190575797365
},
"communicator.exchange": {
"total": 1148.765627283034,
"count": 232631,
"is_parallel": true,
"self": 1148.765627283034
},
"steps_from_proto": {
"total": 89.44855963699229,
"count": 232631,
"is_parallel": true,
"self": 30.397061697814024,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.05149793917826,
"count": 465262,
"is_parallel": true,
"self": 59.05149793917826
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 465.08624929594725,
"count": 232632,
"self": 6.474647197157992,
"children": {
"process_trajectory": {
"total": 149.76772264979013,
"count": 232632,
"self": 148.55089946279145,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2168231869986812,
"count": 10,
"self": 1.2168231869986812
}
}
},
"_update_policy": {
"total": 308.84387944899913,
"count": 97,
"self": 245.58365064900954,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.26022879998959,
"count": 2910,
"self": 63.26022879998959
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.170000000973232e-07,
"count": 1,
"self": 8.170000000973232e-07
},
"TrainerController._save_models": {
"total": 0.09816156899978523,
"count": 1,
"self": 0.001998595000259229,
"children": {
"RLTrainer._checkpoint": {
"total": 0.096162973999526,
"count": 1,
"self": 0.096162973999526
}
}
}
}
}
}
}