Nfanlo's picture
First Push
ed06a0d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7962505221366882,
"min": 0.7962505221366882,
"max": 2.6500117778778076,
"count": 19
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7567.56494140625,
"min": 7567.56494140625,
"max": 24697.44140625,
"count": 19
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 19992.0,
"max": 199984.0,
"count": 19
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 19992.0,
"max": 199984.0,
"count": 19
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.133463859558105,
"min": 1.5524578094482422,
"max": 13.133463859558105,
"count": 19
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2561.025390625,
"min": 209.58180236816406,
"max": 2667.77734375,
"count": 19
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06029072642958651,
"min": 0.06029072642958651,
"max": 0.07884224088458508,
"count": 19
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24116290571834603,
"min": 0.21588641772726913,
"max": 0.3942112044229254,
"count": 19
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17922462694639082,
"min": 0.17922462694639082,
"max": 0.25902328754172604,
"count": 19
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7168985077855633,
"min": 0.6512406222595304,
"max": 1.2951164377086302,
"count": 19
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000273732008756,
"count": 19
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00123666008778,
"count": 19
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.191244,
"count": 19
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.91222,
"count": 19
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0045630756,
"count": 19
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.020619778000000002,
"count": 19
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 19
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 6567.0,
"max": 10945.0,
"count": 19
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.59090909090909,
"min": 6.393939393939394,
"max": 26.09090909090909,
"count": 19
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1126.0,
"min": 211.0,
"max": 1435.0,
"count": 19
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.59090909090909,
"min": 6.393939393939394,
"max": 26.09090909090909,
"count": 19
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1126.0,
"min": 211.0,
"max": 1435.0,
"count": 19
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 19
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 19
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1739036878",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1739037281"
},
"total": 403.194232424,
"count": 1,
"self": 0.42408268599990606,
"children": {
"run_training.setup": {
"total": 0.021529855000039788,
"count": 1,
"self": 0.021529855000039788
},
"TrainerController.start_learning": {
"total": 402.74861988300006,
"count": 1,
"self": 0.35189975899277215,
"children": {
"TrainerController._reset_env": {
"total": 2.0809993199999326,
"count": 1,
"self": 2.0809993199999326
},
"TrainerController.advance": {
"total": 400.2279550590073,
"count": 16992,
"self": 0.36606925101489196,
"children": {
"env_step": {
"total": 280.8414713289967,
"count": 16992,
"self": 212.371148970994,
"children": {
"SubprocessEnvManager._take_step": {
"total": 68.2640947940007,
"count": 16992,
"self": 1.1923049409870146,
"children": {
"TorchPolicy.evaluate": {
"total": 67.07178985301368,
"count": 16992,
"self": 67.07178985301368
}
}
},
"workers": {
"total": 0.20622756400200615,
"count": 16992,
"self": 0.0,
"children": {
"worker_root": {
"total": 401.373826445007,
"count": 16992,
"is_parallel": true,
"self": 215.71651156500639,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002058617999978196,
"count": 1,
"is_parallel": true,
"self": 0.0006587650000255962,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013998529999526,
"count": 10,
"is_parallel": true,
"self": 0.0013998529999526
}
}
},
"UnityEnvironment.step": {
"total": 0.04992671800005155,
"count": 1,
"is_parallel": true,
"self": 0.0005471200000783938,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005468009999276546,
"count": 1,
"is_parallel": true,
"self": 0.0005468009999276546
},
"communicator.exchange": {
"total": 0.04698638700006086,
"count": 1,
"is_parallel": true,
"self": 0.04698638700006086
},
"steps_from_proto": {
"total": 0.001846409999984644,
"count": 1,
"is_parallel": true,
"self": 0.000367069000049014,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00147934099993563,
"count": 10,
"is_parallel": true,
"self": 0.00147934099993563
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 185.65731488000063,
"count": 16991,
"is_parallel": true,
"self": 8.851739224961307,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.91050687399877,
"count": 16991,
"is_parallel": true,
"self": 4.91050687399877
},
"communicator.exchange": {
"total": 143.35022902602725,
"count": 16991,
"is_parallel": true,
"self": 143.35022902602725
},
"steps_from_proto": {
"total": 28.5448397550133,
"count": 16991,
"is_parallel": true,
"self": 5.196130777999315,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.348708977013985,
"count": 169910,
"is_parallel": true,
"self": 23.348708977013985
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 119.02041447899569,
"count": 16992,
"self": 0.426382659982778,
"children": {
"process_trajectory": {
"total": 25.41167894301384,
"count": 16992,
"self": 24.953440774013757,
"children": {
"RLTrainer._checkpoint": {
"total": 0.45823816900008296,
"count": 4,
"self": 0.45823816900008296
}
}
},
"_update_policy": {
"total": 93.18235287599907,
"count": 84,
"self": 37.48941541299496,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.692937463004114,
"count": 4281,
"self": 55.692937463004114
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.889999207895016e-07,
"count": 1,
"self": 8.889999207895016e-07
},
"TrainerController._save_models": {
"total": 0.08776485600014894,
"count": 1,
"self": 0.001131287000134762,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08663356900001418,
"count": 1,
"self": 0.08663356900001418
}
}
}
}
}
}
}