ppo-Huggy / run_logs /timers.json
hookzeng's picture
Huggy
98bc53b verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4009101390838623,
"min": 1.4009101390838623,
"max": 1.4277199506759644,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70031.5,
"min": 69218.5,
"max": 77652.484375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 72.3108504398827,
"min": 69.76803394625176,
"max": 392.2578125,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49316.0,
"min": 49204.0,
"max": 50209.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999930.0,
"min": 49587.0,
"max": 1999930.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999930.0,
"min": 49587.0,
"max": 1999930.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5559611320495605,
"min": 0.06510166823863983,
"max": 2.5559611320495605,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1743.16552734375,
"min": 8.267911911010742,
"max": 1769.521484375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.931996060518925,
"min": 1.8699833298996678,
"max": 4.159036475291223,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2681.6213132739067,
"min": 237.4878828972578,
"max": 2777.424973666668,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.931996060518925,
"min": 1.8699833298996678,
"max": 4.159036475291223,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2681.6213132739067,
"min": 237.4878828972578,
"max": 2777.424973666668,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016899074291642238,
"min": 0.012818643916721661,
"max": 0.021460018191404136,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.050697222874926715,
"min": 0.02783927865869676,
"max": 0.05646782904902163,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0630955871194601,
"min": 0.02129326534147064,
"max": 0.06578394789248705,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18928676135838032,
"min": 0.04258653068294128,
"max": 0.18928676135838032,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7599487467166646e-06,
"min": 3.7599487467166646e-06,
"max": 0.00029533447655517495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1279846240149994e-05,
"min": 1.1279846240149994e-05,
"max": 0.0008438712187096,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10125328333333333,
"min": 0.10125328333333333,
"max": 0.19844482499999994,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30375985,
"min": 0.20764175,
"max": 0.5812903999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.25388383333333e-05,
"min": 7.25388383333333e-05,
"max": 0.004922396767500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021761651499999988,
"min": 0.00021761651499999988,
"max": 0.014066390960000001,
"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": "1713099340",
"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": "1713101859"
},
"total": 2519.247310012,
"count": 1,
"self": 0.7124283329999344,
"children": {
"run_training.setup": {
"total": 0.0586776350000946,
"count": 1,
"self": 0.0586776350000946
},
"TrainerController.start_learning": {
"total": 2518.476204044,
"count": 1,
"self": 4.373927431894117,
"children": {
"TrainerController._reset_env": {
"total": 3.0490363510000407,
"count": 1,
"self": 3.0490363510000407
},
"TrainerController.advance": {
"total": 2510.868368042106,
"count": 233504,
"self": 4.639619965043494,
"children": {
"env_step": {
"total": 2018.5215063300595,
"count": 233504,
"self": 1678.7533068670725,
"children": {
"SubprocessEnvManager._take_step": {
"total": 336.8132443149227,
"count": 233504,
"self": 17.55467112287124,
"children": {
"TorchPolicy.evaluate": {
"total": 319.2585731920515,
"count": 222886,
"self": 319.2585731920515
}
}
},
"workers": {
"total": 2.9549551480643004,
"count": 233504,
"self": 0.0,
"children": {
"worker_root": {
"total": 2510.7909746259206,
"count": 233504,
"is_parallel": true,
"self": 1152.0842979718454,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009142690000771836,
"count": 1,
"is_parallel": true,
"self": 0.0002155820002371911,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006986869998399925,
"count": 2,
"is_parallel": true,
"self": 0.0006986869998399925
}
}
},
"UnityEnvironment.step": {
"total": 0.030882777999977407,
"count": 1,
"is_parallel": true,
"self": 0.0003814669998973841,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020958699997208896,
"count": 1,
"is_parallel": true,
"self": 0.00020958699997208896
},
"communicator.exchange": {
"total": 0.029549071000019467,
"count": 1,
"is_parallel": true,
"self": 0.029549071000019467
},
"steps_from_proto": {
"total": 0.0007426530000884668,
"count": 1,
"is_parallel": true,
"self": 0.00019356400002834562,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005490890000601212,
"count": 2,
"is_parallel": true,
"self": 0.0005490890000601212
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1358.7066766540752,
"count": 233503,
"is_parallel": true,
"self": 41.49645212701148,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.24155759811583,
"count": 233503,
"is_parallel": true,
"self": 86.24155759811583
},
"communicator.exchange": {
"total": 1134.430077805988,
"count": 233503,
"is_parallel": true,
"self": 1134.430077805988
},
"steps_from_proto": {
"total": 96.53858912295982,
"count": 233503,
"is_parallel": true,
"self": 34.79282251878203,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.74576660417779,
"count": 467006,
"is_parallel": true,
"self": 61.74576660417779
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 487.70724174700285,
"count": 233504,
"self": 6.3968131579338205,
"children": {
"process_trajectory": {
"total": 163.60385698506843,
"count": 233504,
"self": 162.25041935006948,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3534376349989543,
"count": 10,
"self": 1.3534376349989543
}
}
},
"_update_policy": {
"total": 317.7065716040006,
"count": 97,
"self": 254.78514029599796,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.92143130800264,
"count": 2910,
"self": 62.92143130800264
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.228999735758407e-06,
"count": 1,
"self": 1.228999735758407e-06
},
"TrainerController._save_models": {
"total": 0.18487099000003582,
"count": 1,
"self": 0.0031156740001279104,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1817553159999079,
"count": 1,
"self": 0.1817553159999079
}
}
}
}
}
}
}