Michael8888's picture
First Push
0a7740d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7869237065315247,
"min": 0.7869237065315247,
"max": 2.8360538482666016,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7478.9228515625,
"min": 7478.9228515625,
"max": 28950.4375,
"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": 12.736723899841309,
"min": 0.31098672747612,
"max": 12.736723899841309,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2483.6611328125,
"min": 60.331424713134766,
"max": 2565.29150390625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07046566387112298,
"min": 0.059007227446629396,
"max": 0.07670735880902593,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2818626554844919,
"min": 0.23602890978651758,
"max": 0.3835367940451297,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21431858538120402,
"min": 0.13122465556450919,
"max": 0.28001882428047703,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8572743415248161,
"min": 0.5248986222580367,
"max": 1.2666264591263787,
"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.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.Environment.CumulativeReward.mean": {
"value": 25.454545454545453,
"min": 3.522727272727273,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1120.0,
"min": 155.0,
"max": 1368.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.454545454545453,
"min": 3.522727272727273,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1120.0,
"min": 155.0,
"max": 1368.0,
"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": "1770702293",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1770702722"
},
"total": 429.0390105140002,
"count": 1,
"self": 0.43004244200005814,
"children": {
"run_training.setup": {
"total": 0.022968984000044657,
"count": 1,
"self": 0.022968984000044657
},
"TrainerController.start_learning": {
"total": 428.5859990880001,
"count": 1,
"self": 0.34179360699613426,
"children": {
"TrainerController._reset_env": {
"total": 3.1674322880001,
"count": 1,
"self": 3.1674322880001
},
"TrainerController.advance": {
"total": 425.0009112180039,
"count": 18192,
"self": 0.3538673000007293,
"children": {
"env_step": {
"total": 304.2132048209976,
"count": 18192,
"self": 237.42505244198992,
"children": {
"SubprocessEnvManager._take_step": {
"total": 66.5770830880067,
"count": 18192,
"self": 1.224857908981221,
"children": {
"TorchPolicy.evaluate": {
"total": 65.35222517902548,
"count": 18192,
"self": 65.35222517902548
}
}
},
"workers": {
"total": 0.2110692910009675,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 426.71666814199443,
"count": 18192,
"is_parallel": true,
"self": 218.07993234698552,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004316691999974864,
"count": 1,
"is_parallel": true,
"self": 0.002992515000187268,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013241769997875963,
"count": 10,
"is_parallel": true,
"self": 0.0013241769997875963
}
}
},
"UnityEnvironment.step": {
"total": 0.06679421400008323,
"count": 1,
"is_parallel": true,
"self": 0.0005724520001422206,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003752689999600989,
"count": 1,
"is_parallel": true,
"self": 0.0003752689999600989
},
"communicator.exchange": {
"total": 0.06109572500008653,
"count": 1,
"is_parallel": true,
"self": 0.06109572500008653
},
"steps_from_proto": {
"total": 0.004750767999894379,
"count": 1,
"is_parallel": true,
"self": 0.0033878860001550493,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013628819997393293,
"count": 10,
"is_parallel": true,
"self": 0.0013628819997393293
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 208.63673579500892,
"count": 18191,
"is_parallel": true,
"self": 9.84906893898551,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.191950005012586,
"count": 18191,
"is_parallel": true,
"self": 5.191950005012586
},
"communicator.exchange": {
"total": 159.28116701000067,
"count": 18191,
"is_parallel": true,
"self": 159.28116701000067
},
"steps_from_proto": {
"total": 34.31454984101015,
"count": 18191,
"is_parallel": true,
"self": 6.3978404040515215,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.916709436958627,
"count": 181910,
"is_parallel": true,
"self": 27.916709436958627
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 120.4338390970056,
"count": 18192,
"self": 0.41342897099775655,
"children": {
"process_trajectory": {
"total": 25.885821674008184,
"count": 18192,
"self": 25.50778790600839,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3780337679997956,
"count": 4,
"self": 0.3780337679997956
}
}
},
"_update_policy": {
"total": 94.13458845199966,
"count": 90,
"self": 39.41811242400581,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.71647602799385,
"count": 4587,
"self": 54.71647602799385
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1189999895577785e-06,
"count": 1,
"self": 1.1189999895577785e-06
},
"TrainerController._save_models": {
"total": 0.07586085599996295,
"count": 1,
"self": 0.0007193909998477466,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0751414650001152,
"count": 1,
"self": 0.0751414650001152
}
}
}
}
}
}
}