ppo-Huggy / run_logs /timers.json
pierrelb's picture
Huggy
bad0f01 verified
raw
history blame contribute delete
No virus
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4015215635299683,
"min": 1.4015215635299683,
"max": 1.4281790256500244,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71226.7265625,
"min": 68740.9375,
"max": 76938.0,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 94.20722433460077,
"min": 87.65780141843972,
"max": 394.68992248062017,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49553.0,
"min": 48896.0,
"max": 50915.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999997.0,
"min": 49893.0,
"max": 1999997.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999997.0,
"min": 49893.0,
"max": 1999997.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3861024379730225,
"min": 0.020675694569945335,
"max": 2.445248603820801,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1255.08984375,
"min": 2.6258132457733154,
"max": 1350.647705078125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6612091135842717,
"min": 1.8890649453392179,
"max": 3.8702759058121217,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1925.795993745327,
"min": 239.91124805808067,
"max": 2116.514584839344,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6612091135842717,
"min": 1.8890649453392179,
"max": 3.8702759058121217,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1925.795993745327,
"min": 239.91124805808067,
"max": 2116.514584839344,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014959649843230081,
"min": 0.012267587379190243,
"max": 0.01939250537672908,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.044878949529690244,
"min": 0.02691767347520605,
"max": 0.058177516130187235,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05274464074108335,
"min": 0.02379757181430856,
"max": 0.057683908566832545,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15823392222325006,
"min": 0.04759514362861712,
"max": 0.1717605027059714,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2177989274333445e-06,
"min": 3.2177989274333445e-06,
"max": 0.00029537865154044996,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.653396782300034e-06,
"min": 9.653396782300034e-06,
"max": 0.0008440971186342999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10107256666666666,
"min": 0.10107256666666666,
"max": 0.19845954999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3032177,
"min": 0.20731025000000008,
"max": 0.5813657000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.352107666666687e-05,
"min": 6.352107666666687e-05,
"max": 0.004923131544999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001905632300000006,
"min": 0.0001905632300000006,
"max": 0.014070148429999997,
"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": "1716501766",
"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": "1716504266"
},
"total": 2500.401086628,
"count": 1,
"self": 0.43588238700021975,
"children": {
"run_training.setup": {
"total": 0.05535823800005346,
"count": 1,
"self": 0.05535823800005346
},
"TrainerController.start_learning": {
"total": 2499.909846003,
"count": 1,
"self": 4.4718097632289755,
"children": {
"TrainerController._reset_env": {
"total": 3.0350652429999627,
"count": 1,
"self": 3.0350652429999627
},
"TrainerController.advance": {
"total": 2492.282704656771,
"count": 231938,
"self": 4.816495185867552,
"children": {
"env_step": {
"total": 1979.5056801629871,
"count": 231938,
"self": 1635.4530692358712,
"children": {
"SubprocessEnvManager._take_step": {
"total": 341.1119592490454,
"count": 231938,
"self": 17.128518064092532,
"children": {
"TorchPolicy.evaluate": {
"total": 323.9834411849529,
"count": 223006,
"self": 323.9834411849529
}
}
},
"workers": {
"total": 2.9406516780704806,
"count": 231938,
"self": 0.0,
"children": {
"worker_root": {
"total": 2492.4742850380717,
"count": 231938,
"is_parallel": true,
"self": 1175.1366344089959,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008985649999431189,
"count": 1,
"is_parallel": true,
"self": 0.0002516119998290378,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006469530001140811,
"count": 2,
"is_parallel": true,
"self": 0.0006469530001140811
}
}
},
"UnityEnvironment.step": {
"total": 0.031228067000029114,
"count": 1,
"is_parallel": true,
"self": 0.00039998900024329487,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002071799999612267,
"count": 1,
"is_parallel": true,
"self": 0.0002071799999612267
},
"communicator.exchange": {
"total": 0.029837550999900486,
"count": 1,
"is_parallel": true,
"self": 0.029837550999900486
},
"steps_from_proto": {
"total": 0.0007833469999241061,
"count": 1,
"is_parallel": true,
"self": 0.00022734799995305366,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005559989999710524,
"count": 2,
"is_parallel": true,
"self": 0.0005559989999710524
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1317.3376506290758,
"count": 231937,
"is_parallel": true,
"self": 39.9928419860903,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.15693210404424,
"count": 231937,
"is_parallel": true,
"self": 85.15693210404424
},
"communicator.exchange": {
"total": 1099.6693619209714,
"count": 231937,
"is_parallel": true,
"self": 1099.6693619209714
},
"steps_from_proto": {
"total": 92.51851461796991,
"count": 231937,
"is_parallel": true,
"self": 34.859484054046334,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.65903056392358,
"count": 463874,
"is_parallel": true,
"self": 57.65903056392358
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 507.9605293079162,
"count": 231938,
"self": 6.747202700900743,
"children": {
"process_trajectory": {
"total": 157.7440474760151,
"count": 231938,
"self": 156.4401892760161,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3038581999990129,
"count": 10,
"self": 1.3038581999990129
}
}
},
"_update_policy": {
"total": 343.46927913100035,
"count": 97,
"self": 278.4819180309844,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.98736110001596,
"count": 2910,
"self": 64.98736110001596
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.44300020110677e-06,
"count": 1,
"self": 1.44300020110677e-06
},
"TrainerController._save_models": {
"total": 0.12026489700019738,
"count": 1,
"self": 0.0019946420002270315,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11827025499997035,
"count": 1,
"self": 0.11827025499997035
}
}
}
}
}
}
}