rl-ppo-Huggy / run_logs /timers.json
banbao990's picture
Huggy
54b935c verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4030208587646484,
"min": 1.4030208587646484,
"max": 1.4167375564575195,
"count": 28
},
"Huggy.Policy.Entropy.sum": {
"value": 68522.1328125,
"min": 59354.21875,
"max": 73282.3828125,
"count": 28
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 111.3108108108108,
"min": 89.61010830324909,
"max": 114.45080091533181,
"count": 28
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49422.0,
"min": 40508.0,
"max": 50175.0,
"count": 28
},
"Huggy.Step.mean": {
"value": 1999959.0,
"min": 649888.0,
"max": 1999959.0,
"count": 28
},
"Huggy.Step.sum": {
"value": 1999959.0,
"min": 649888.0,
"max": 1999959.0,
"count": 28
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.259976387023926,
"min": 2.259976387023926,
"max": 2.4814703464508057,
"count": 28
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1003.4295654296875,
"min": 1003.4295654296875,
"max": 1316.1204833984375,
"count": 28
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.349322329770337,
"min": 3.349322329770337,
"max": 4.0203424112245925,
"count": 28
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1487.0991144180298,
"min": 1487.0991144180298,
"max": 2227.269695818424,
"count": 28
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.349322329770337,
"min": 3.349322329770337,
"max": 4.0203424112245925,
"count": 28
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1487.0991144180298,
"min": 1487.0991144180298,
"max": 2227.269695818424,
"count": 28
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014490920453519922,
"min": 0.014391183886780507,
"max": 0.019386810514940105,
"count": 28
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04347276136055977,
"min": 0.01456038093844351,
"max": 0.05607217766422157,
"count": 28
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.047175444248649806,
"min": 0.039400661115845045,
"max": 0.05917017987618844,
"count": 28
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14152633274594942,
"min": 0.04377048735817273,
"max": 0.17305040471255778,
"count": 28
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.329548556850002e-06,
"min": 4.329548556850002e-06,
"max": 0.00020555073148310004,
"count": 28
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.2988645670550007e-05,
"min": 1.2988645670550007e-05,
"max": 0.0005981629006123999,
"count": 28
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10144315,
"min": 0.10144315,
"max": 0.16851690000000005,
"count": 28
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30432945,
"min": 0.16851690000000005,
"max": 0.49938759999999993,
"count": 28
},
"Huggy.Policy.Beta.mean": {
"value": 8.201318500000004e-05,
"min": 8.201318500000004e-05,
"max": 0.003428993310000001,
"count": 28
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002460395550000001,
"min": 0.0002460395550000001,
"max": 0.009979441240000001,
"count": 28
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 28
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 28
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1721032549",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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 --resume",
"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": "1721034394"
},
"total": 1844.638750988,
"count": 1,
"self": 0.48667016800004603,
"children": {
"run_training.setup": {
"total": 0.05314881300000707,
"count": 1,
"self": 0.05314881300000707
},
"TrainerController.start_learning": {
"total": 1844.098932007,
"count": 1,
"self": 3.4943893100271453,
"children": {
"TrainerController._reset_env": {
"total": 2.0812743540000156,
"count": 1,
"self": 2.0812743540000156
},
"TrainerController.advance": {
"total": 1838.3985627279724,
"count": 161958,
"self": 3.60097430296355,
"children": {
"env_step": {
"total": 1478.3558977870362,
"count": 161958,
"self": 1220.126678509991,
"children": {
"SubprocessEnvManager._take_step": {
"total": 255.8928482909871,
"count": 161958,
"self": 12.614806746031832,
"children": {
"TorchPolicy.evaluate": {
"total": 243.27804154495527,
"count": 155203,
"self": 243.27804154495527
}
}
},
"workers": {
"total": 2.3363709860578865,
"count": 161958,
"self": 0.0,
"children": {
"worker_root": {
"total": 1838.35913645295,
"count": 161958,
"is_parallel": true,
"self": 858.2563159868846,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009047790000522582,
"count": 1,
"is_parallel": true,
"self": 0.00025120100008280133,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006535779999694569,
"count": 2,
"is_parallel": true,
"self": 0.0006535779999694569
}
}
},
"UnityEnvironment.step": {
"total": 0.030949259999943024,
"count": 1,
"is_parallel": true,
"self": 0.00043012699984501523,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022382400004516967,
"count": 1,
"is_parallel": true,
"self": 0.00022382400004516967
},
"communicator.exchange": {
"total": 0.02953334400001495,
"count": 1,
"is_parallel": true,
"self": 0.02953334400001495
},
"steps_from_proto": {
"total": 0.0007619650000378897,
"count": 1,
"is_parallel": true,
"self": 0.0002089309999746547,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000553034000063235,
"count": 2,
"is_parallel": true,
"self": 0.000553034000063235
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 980.1028204660654,
"count": 161957,
"is_parallel": true,
"self": 29.18719778084335,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 63.83460428097624,
"count": 161957,
"is_parallel": true,
"self": 63.83460428097624
},
"communicator.exchange": {
"total": 817.636219266137,
"count": 161957,
"is_parallel": true,
"self": 817.636219266137
},
"steps_from_proto": {
"total": 69.4447991381088,
"count": 161957,
"is_parallel": true,
"self": 26.39542412009598,
"children": {
"_process_rank_one_or_two_observation": {
"total": 43.049375018012825,
"count": 323914,
"is_parallel": true,
"self": 43.049375018012825
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 356.44169063797267,
"count": 161958,
"self": 5.032306260951486,
"children": {
"process_trajectory": {
"total": 121.91670213002237,
"count": 161958,
"self": 120.94643489202224,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9702672380001331,
"count": 7,
"self": 0.9702672380001331
}
}
},
"_update_policy": {
"total": 229.4926822469988,
"count": 67,
"self": 184.90064742699929,
"children": {
"TorchPPOOptimizer.update": {
"total": 44.592034819999526,
"count": 2010,
"self": 44.592034819999526
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.860001798893791e-07,
"count": 1,
"self": 8.860001798893791e-07
},
"TrainerController._save_models": {
"total": 0.12470472900031382,
"count": 1,
"self": 0.003018563000296126,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12168616600001769,
"count": 1,
"self": 0.12168616600001769
}
}
}
}
}
}
}