Retrial9842's picture
First Push
0ab6141
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9933382272720337,
"min": 0.9811428189277649,
"max": 2.853519916534424,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9473.466796875,
"min": 9473.466796875,
"max": 29254.287109375,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.044002532958984,
"min": 0.33523839712142944,
"max": 13.044002532958984,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2543.58056640625,
"min": 65.03624725341797,
"max": 2649.512451171875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06747423672755294,
"min": 0.06421348748022312,
"max": 0.0790227473651826,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26989694691021177,
"min": 0.2568539499208925,
"max": 0.35568130628135075,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2050740299563782,
"min": 0.13757360245868125,
"max": 0.27898961071874584,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8202961198255128,
"min": 0.550294409834725,
"max": 1.394948053593729,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.34090909090909,
"min": 3.909090909090909,
"max": 25.886363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1115.0,
"min": 172.0,
"max": 1416.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.34090909090909,
"min": 3.909090909090909,
"max": 25.886363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1115.0,
"min": 172.0,
"max": 1416.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1686111431",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1686111925"
},
"total": 493.57015855699996,
"count": 1,
"self": 0.43507999599989944,
"children": {
"run_training.setup": {
"total": 0.04900174300001936,
"count": 1,
"self": 0.04900174300001936
},
"TrainerController.start_learning": {
"total": 493.08607681800004,
"count": 1,
"self": 0.5693065170062255,
"children": {
"TrainerController._reset_env": {
"total": 3.6996778430000177,
"count": 1,
"self": 3.6996778430000177
},
"TrainerController.advance": {
"total": 488.6575374859939,
"count": 18200,
"self": 0.2814067759928207,
"children": {
"env_step": {
"total": 488.37613071000106,
"count": 18200,
"self": 356.88567577100764,
"children": {
"SubprocessEnvManager._take_step": {
"total": 131.2020938289984,
"count": 18200,
"self": 1.8447752609930035,
"children": {
"TorchPolicy.evaluate": {
"total": 129.35731856800538,
"count": 18200,
"self": 129.35731856800538
}
}
},
"workers": {
"total": 0.28836110999503717,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 491.4364860499968,
"count": 18200,
"is_parallel": true,
"self": 229.96346558999824,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005728836999992382,
"count": 1,
"is_parallel": true,
"self": 0.00396948399992425,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017593530000681312,
"count": 10,
"is_parallel": true,
"self": 0.0017593530000681312
}
}
},
"UnityEnvironment.step": {
"total": 0.047125665999999455,
"count": 1,
"is_parallel": true,
"self": 0.0004969109999706234,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00033214000001180466,
"count": 1,
"is_parallel": true,
"self": 0.00033214000001180466
},
"communicator.exchange": {
"total": 0.04462674199999128,
"count": 1,
"is_parallel": true,
"self": 0.04462674199999128
},
"steps_from_proto": {
"total": 0.0016698730000257456,
"count": 1,
"is_parallel": true,
"self": 0.0003200379999270808,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013498350000986648,
"count": 10,
"is_parallel": true,
"self": 0.0013498350000986648
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 261.47302045999857,
"count": 18199,
"is_parallel": true,
"self": 10.783372024007235,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.766797133995908,
"count": 18199,
"is_parallel": true,
"self": 5.766797133995908
},
"communicator.exchange": {
"total": 206.85142587399253,
"count": 18199,
"is_parallel": true,
"self": 206.85142587399253
},
"steps_from_proto": {
"total": 38.0714254280029,
"count": 18199,
"is_parallel": true,
"self": 7.149931267015575,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.921494160987322,
"count": 181990,
"is_parallel": true,
"self": 30.921494160987322
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.1778999957386986e-05,
"count": 1,
"self": 4.1778999957386986e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 484.76649589399614,
"count": 460220,
"is_parallel": true,
"self": 10.584608051989846,
"children": {
"process_trajectory": {
"total": 266.8367116540061,
"count": 460220,
"is_parallel": true,
"self": 266.039592217006,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7971194370001058,
"count": 4,
"is_parallel": true,
"self": 0.7971194370001058
}
}
},
"_update_policy": {
"total": 207.3451761880002,
"count": 90,
"is_parallel": true,
"self": 79.34019726300187,
"children": {
"TorchPPOOptimizer.update": {
"total": 128.00497892499834,
"count": 4587,
"is_parallel": true,
"self": 128.00497892499834
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15951319299995248,
"count": 1,
"self": 0.0010782579998931396,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15843493500005934,
"count": 1,
"self": 0.15843493500005934
}
}
}
}
}
}
}