ppo-Huggy / run_logs /timers.json
davidkh's picture
Huggy
6ad3406 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.407684564590454,
"min": 1.407684564590454,
"max": 1.430965781211853,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71003.609375,
"min": 69089.265625,
"max": 76941.890625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 74.17091454272864,
"min": 74.17091454272864,
"max": 383.2671755725191,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49472.0,
"min": 49247.0,
"max": 50208.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999978.0,
"min": 49879.0,
"max": 1999978.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999978.0,
"min": 49879.0,
"max": 1999978.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4701550006866455,
"min": 0.17791137099266052,
"max": 2.5089752674102783,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1645.123291015625,
"min": 23.12847900390625,
"max": 1645.123291015625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.873437262064702,
"min": 1.7295905484603002,
"max": 4.076100115303521,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2579.7092165350914,
"min": 224.84677129983902,
"max": 2606.618995010853,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.873437262064702,
"min": 1.7295905484603002,
"max": 4.076100115303521,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2579.7092165350914,
"min": 224.84677129983902,
"max": 2606.618995010853,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015044492500763026,
"min": 0.013833807678505157,
"max": 0.0200762666066617,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04513347750228908,
"min": 0.027667615357010313,
"max": 0.06022879981998509,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05985826812684536,
"min": 0.021603192854672673,
"max": 0.06335399602022436,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17957480438053608,
"min": 0.043206385709345346,
"max": 0.1900619880606731,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.912198695966662e-06,
"min": 3.912198695966662e-06,
"max": 0.0002953659015446999,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1736596087899988e-05,
"min": 1.1736596087899988e-05,
"max": 0.0008441637186120999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10130403333333332,
"min": 0.10130403333333332,
"max": 0.1984553,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30391209999999996,
"min": 0.20773994999999995,
"max": 0.5813879,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.507126333333329e-05,
"min": 7.507126333333329e-05,
"max": 0.00492291947,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022521378999999987,
"min": 0.00022521378999999987,
"max": 0.014071256209999999,
"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": "1712477333",
"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": "1712479832"
},
"total": 2499.185163563,
"count": 1,
"self": 0.4463198400003421,
"children": {
"run_training.setup": {
"total": 0.08371135700008381,
"count": 1,
"self": 0.08371135700008381
},
"TrainerController.start_learning": {
"total": 2498.6551323659996,
"count": 1,
"self": 4.9427437780941545,
"children": {
"TrainerController._reset_env": {
"total": 3.4567595460000575,
"count": 1,
"self": 3.4567595460000575
},
"TrainerController.advance": {
"total": 2490.1401690249054,
"count": 233148,
"self": 4.808302399796503,
"children": {
"env_step": {
"total": 2001.3866122161724,
"count": 233148,
"self": 1662.4992317770623,
"children": {
"SubprocessEnvManager._take_step": {
"total": 335.8496007000882,
"count": 233148,
"self": 17.58340798515701,
"children": {
"TorchPolicy.evaluate": {
"total": 318.2661927149312,
"count": 222922,
"self": 318.2661927149312
}
}
},
"workers": {
"total": 3.0377797390218575,
"count": 233148,
"self": 0.0,
"children": {
"worker_root": {
"total": 2491.1918758390966,
"count": 233148,
"is_parallel": true,
"self": 1147.5446645341212,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008259640000005675,
"count": 1,
"is_parallel": true,
"self": 0.0002176390000840911,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006083249999164764,
"count": 2,
"is_parallel": true,
"self": 0.0006083249999164764
}
}
},
"UnityEnvironment.step": {
"total": 0.031865847999938524,
"count": 1,
"is_parallel": true,
"self": 0.0003832949998923141,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021313000002010085,
"count": 1,
"is_parallel": true,
"self": 0.00021313000002010085
},
"communicator.exchange": {
"total": 0.03048908100004155,
"count": 1,
"is_parallel": true,
"self": 0.03048908100004155
},
"steps_from_proto": {
"total": 0.0007803419999845573,
"count": 1,
"is_parallel": true,
"self": 0.00020808000010674732,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00057226199987781,
"count": 2,
"is_parallel": true,
"self": 0.00057226199987781
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1343.6472113049754,
"count": 233147,
"is_parallel": true,
"self": 40.972117108990005,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.75578098599385,
"count": 233147,
"is_parallel": true,
"self": 85.75578098599385
},
"communicator.exchange": {
"total": 1121.4376384980715,
"count": 233147,
"is_parallel": true,
"self": 1121.4376384980715
},
"steps_from_proto": {
"total": 95.48167471191994,
"count": 233147,
"is_parallel": true,
"self": 34.178569532966435,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.3031051789535,
"count": 466294,
"is_parallel": true,
"self": 61.3031051789535
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 483.9452544089363,
"count": 233148,
"self": 6.9767271340246,
"children": {
"process_trajectory": {
"total": 159.27078362191048,
"count": 233148,
"self": 157.90544167490998,
"children": {
"RLTrainer._checkpoint": {
"total": 1.365341947000502,
"count": 10,
"self": 1.365341947000502
}
}
},
"_update_policy": {
"total": 317.6977436530012,
"count": 97,
"self": 254.21036559801007,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.487378054991154,
"count": 2910,
"self": 63.487378054991154
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.010001693037339e-07,
"count": 1,
"self": 8.010001693037339e-07
},
"TrainerController._save_models": {
"total": 0.11545921600009024,
"count": 1,
"self": 0.0019364509998922586,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11352276500019798,
"count": 1,
"self": 0.11352276500019798
}
}
}
}
}
}
}