ppo-Huggy / run_logs /timers.json
Rxwang's picture
Huggy
8bb2f67
raw
history blame
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4121044874191284,
"min": 1.4120982885360718,
"max": 1.428870439529419,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71521.6796875,
"min": 69410.9375,
"max": 76832.8984375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 77.00468018720748,
"min": 77.00468018720748,
"max": 380.793893129771,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49360.0,
"min": 49325.0,
"max": 49970.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999954.0,
"min": 49718.0,
"max": 1999954.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999954.0,
"min": 49718.0,
"max": 1999954.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4490065574645996,
"min": 0.11753512918949127,
"max": 2.514531373977661,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1569.813232421875,
"min": 15.279566764831543,
"max": 1569.813232421875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.793956893282636,
"min": 1.7690066224107375,
"max": 4.060571325133587,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2431.9263685941696,
"min": 229.97086091339588,
"max": 2431.9263685941696,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.793956893282636,
"min": 1.7690066224107375,
"max": 4.060571325133587,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2431.9263685941696,
"min": 229.97086091339588,
"max": 2431.9263685941696,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01559161001738782,
"min": 0.014011936107575215,
"max": 0.0192455784294806,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04677483005216346,
"min": 0.02802387221515043,
"max": 0.0577367352884418,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.062262135785486956,
"min": 0.022999388414124647,
"max": 0.062279524219532804,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18678640735646088,
"min": 0.045998776828249294,
"max": 0.18678640735646088,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.414598861833331e-06,
"min": 3.414598861833331e-06,
"max": 0.000295384426538525,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0243796585499992e-05,
"min": 1.0243796585499992e-05,
"max": 0.0008442228185924002,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10113816666666668,
"min": 0.10113816666666668,
"max": 0.19846147500000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30341450000000003,
"min": 0.20740390000000003,
"max": 0.5814076000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.679451666666663e-05,
"min": 6.679451666666663e-05,
"max": 0.004923227602500002,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020038354999999988,
"min": 0.00020038354999999988,
"max": 0.01407223924,
"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": "1691998529",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1692001020"
},
"total": 2490.737399502,
"count": 1,
"self": 0.74862470700009,
"children": {
"run_training.setup": {
"total": 0.05170216499982416,
"count": 1,
"self": 0.05170216499982416
},
"TrainerController.start_learning": {
"total": 2489.93707263,
"count": 1,
"self": 4.537055218016576,
"children": {
"TrainerController._reset_env": {
"total": 4.463208185999974,
"count": 1,
"self": 4.463208185999974
},
"TrainerController.advance": {
"total": 2480.7429469339836,
"count": 232764,
"self": 4.612886708078349,
"children": {
"env_step": {
"total": 1906.0929568390798,
"count": 232764,
"self": 1609.048276672095,
"children": {
"SubprocessEnvManager._take_step": {
"total": 294.05046744394053,
"count": 232764,
"self": 17.099373520778954,
"children": {
"TorchPolicy.evaluate": {
"total": 276.9510939231616,
"count": 222956,
"self": 276.9510939231616
}
}
},
"workers": {
"total": 2.9942127230442566,
"count": 232764,
"self": 0.0,
"children": {
"worker_root": {
"total": 2482.1058180528476,
"count": 232764,
"is_parallel": true,
"self": 1167.81391254679,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008664970000609173,
"count": 1,
"is_parallel": true,
"self": 0.00023536399999102287,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006311330000698945,
"count": 2,
"is_parallel": true,
"self": 0.0006311330000698945
}
}
},
"UnityEnvironment.step": {
"total": 0.05163339899991115,
"count": 1,
"is_parallel": true,
"self": 0.0003864849998080899,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022838100016997487,
"count": 1,
"is_parallel": true,
"self": 0.00022838100016997487
},
"communicator.exchange": {
"total": 0.050109070999951655,
"count": 1,
"is_parallel": true,
"self": 0.050109070999951655
},
"steps_from_proto": {
"total": 0.0009094619999814313,
"count": 1,
"is_parallel": true,
"self": 0.00023603900012858503,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006734229998528463,
"count": 2,
"is_parallel": true,
"self": 0.0006734229998528463
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1314.2919055060574,
"count": 232763,
"is_parallel": true,
"self": 40.83645521309677,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.88647546897573,
"count": 232763,
"is_parallel": true,
"self": 82.88647546897573
},
"communicator.exchange": {
"total": 1089.520170904909,
"count": 232763,
"is_parallel": true,
"self": 1089.520170904909
},
"steps_from_proto": {
"total": 101.04880391907591,
"count": 232763,
"is_parallel": true,
"self": 36.08120621615285,
"children": {
"_process_rank_one_or_two_observation": {
"total": 64.96759770292306,
"count": 465526,
"is_parallel": true,
"self": 64.96759770292306
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 570.0371033868257,
"count": 232764,
"self": 6.777275154772951,
"children": {
"process_trajectory": {
"total": 142.6458599180512,
"count": 232764,
"self": 141.2119666590513,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4338932589998876,
"count": 10,
"self": 1.4338932589998876
}
}
},
"_update_policy": {
"total": 420.61396831400157,
"count": 97,
"self": 358.64405950399555,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.96990881000602,
"count": 2910,
"self": 61.96990881000602
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4099996406002901e-06,
"count": 1,
"self": 1.4099996406002901e-06
},
"TrainerController._save_models": {
"total": 0.1938608820000809,
"count": 1,
"self": 0.0028094350000174018,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1910514470000635,
"count": 1,
"self": 0.1910514470000635
}
}
}
}
}
}
}