YoavWigelman's picture
First Push
b8b5cd3
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9092493653297424,
"min": 0.9092493653297424,
"max": 2.870939016342163,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8691.5146484375,
"min": 8691.5146484375,
"max": 29527.607421875,
"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": 13.080718040466309,
"min": 0.29442957043647766,
"max": 13.080718040466309,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2550.739990234375,
"min": 57.11933898925781,
"max": 2642.867919921875,
"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": 0.0718248433232457,
"min": 0.06270578800330814,
"max": 0.0739966535561846,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2872993732929828,
"min": 0.25533638784876456,
"max": 0.36998326778092294,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19338439572967736,
"min": 0.10504633103447109,
"max": 0.2838130255101943,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7735375829187094,
"min": 0.42018532413788434,
"max": 1.3868665651363485,
"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": 25.568181818181817,
"min": 3.090909090909091,
"max": 26.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1125.0,
"min": 136.0,
"max": 1430.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.568181818181817,
"min": 3.090909090909091,
"max": 26.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1125.0,
"min": 136.0,
"max": 1430.0,
"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": "1685885883",
"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": "1685886326"
},
"total": 442.672658262,
"count": 1,
"self": 0.386089949000052,
"children": {
"run_training.setup": {
"total": 0.041514398000003894,
"count": 1,
"self": 0.041514398000003894
},
"TrainerController.start_learning": {
"total": 442.24505391499997,
"count": 1,
"self": 0.5055312550027793,
"children": {
"TrainerController._reset_env": {
"total": 3.711205382000003,
"count": 1,
"self": 3.711205382000003
},
"TrainerController.advance": {
"total": 437.8869642609973,
"count": 18202,
"self": 0.23730751400535155,
"children": {
"env_step": {
"total": 437.6496567469919,
"count": 18202,
"self": 319.42130803399266,
"children": {
"SubprocessEnvManager._take_step": {
"total": 117.98900813799594,
"count": 18202,
"self": 1.8073253120045365,
"children": {
"TorchPolicy.evaluate": {
"total": 116.1816828259914,
"count": 18202,
"self": 116.1816828259914
}
}
},
"workers": {
"total": 0.23934057500332528,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 440.7454919060017,
"count": 18202,
"is_parallel": true,
"self": 207.52355017800562,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0059568289999560875,
"count": 1,
"is_parallel": true,
"self": 0.004531184999905236,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001425644000050852,
"count": 10,
"is_parallel": true,
"self": 0.001425644000050852
}
}
},
"UnityEnvironment.step": {
"total": 0.03345231799994508,
"count": 1,
"is_parallel": true,
"self": 0.0005695689999356546,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00032210900008067256,
"count": 1,
"is_parallel": true,
"self": 0.00032210900008067256
},
"communicator.exchange": {
"total": 0.03059179599995332,
"count": 1,
"is_parallel": true,
"self": 0.03059179599995332
},
"steps_from_proto": {
"total": 0.0019688439999754337,
"count": 1,
"is_parallel": true,
"self": 0.00037571199993635673,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001593132000039077,
"count": 10,
"is_parallel": true,
"self": 0.001593132000039077
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 233.22194172799607,
"count": 18201,
"is_parallel": true,
"self": 9.493381493004563,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.066712229995346,
"count": 18201,
"is_parallel": true,
"self": 5.066712229995346
},
"communicator.exchange": {
"total": 186.60342581498912,
"count": 18201,
"is_parallel": true,
"self": 186.60342581498912
},
"steps_from_proto": {
"total": 32.058422190007036,
"count": 18201,
"is_parallel": true,
"self": 6.004506097003741,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.053916093003295,
"count": 182010,
"is_parallel": true,
"self": 26.053916093003295
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010105699993800954,
"count": 1,
"self": 0.00010105699993800954,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 434.5583237620003,
"count": 414371,
"is_parallel": true,
"self": 9.190536542996028,
"children": {
"process_trajectory": {
"total": 237.994306702004,
"count": 414371,
"is_parallel": true,
"self": 237.0217844720039,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9725222300000951,
"count": 4,
"is_parallel": true,
"self": 0.9725222300000951
}
}
},
"_update_policy": {
"total": 187.3734805170003,
"count": 90,
"is_parallel": true,
"self": 70.21546558100238,
"children": {
"TorchPPOOptimizer.update": {
"total": 117.15801493599793,
"count": 4587,
"is_parallel": true,
"self": 117.15801493599793
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14125195999997686,
"count": 1,
"self": 0.0008660449999524644,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1403859150000244,
"count": 1,
"self": 0.1403859150000244
}
}
}
}
}
}
}