N0de's picture
First Push
5e07337 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0650320053100586,
"min": 1.0650320053100586,
"max": 2.879382371902466,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10227.501953125,
"min": 10227.501953125,
"max": 29582.7734375,
"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": 12.709700584411621,
"min": 0.30270373821258545,
"max": 12.709700584411621,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2478.3916015625,
"min": 58.724525451660156,
"max": 2559.3447265625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06560993966562748,
"min": 0.0628726412268246,
"max": 0.07381598338263347,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2624397586625099,
"min": 0.2514905649072984,
"max": 0.3690799169131673,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2422183429931893,
"min": 0.10453077147751316,
"max": 0.284000279155432,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9688733719727572,
"min": 0.41812308591005265,
"max": 1.42000139577716,
"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": 24.954545454545453,
"min": 2.909090909090909,
"max": 25.227272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1098.0,
"min": 128.0,
"max": 1384.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.954545454545453,
"min": 2.909090909090909,
"max": 25.227272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1098.0,
"min": 128.0,
"max": 1384.0,
"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": "1711522913",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/home/node/WORK/WORKSPACE/ENVS/miscs/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./trained-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --force",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1711523300"
},
"total": 386.5635442329999,
"count": 1,
"self": 0.3204144419999011,
"children": {
"run_training.setup": {
"total": 0.02290904899996349,
"count": 1,
"self": 0.02290904899996349
},
"TrainerController.start_learning": {
"total": 386.22022074200004,
"count": 1,
"self": 0.5447479560016291,
"children": {
"TrainerController._reset_env": {
"total": 2.603208147000032,
"count": 1,
"self": 2.603208147000032
},
"TrainerController.advance": {
"total": 382.98290273399834,
"count": 18204,
"self": 0.26331412599392934,
"children": {
"env_step": {
"total": 382.7195886080044,
"count": 18204,
"self": 240.77313810502255,
"children": {
"SubprocessEnvManager._take_step": {
"total": 141.66841605399713,
"count": 18204,
"self": 1.51391587598755,
"children": {
"TorchPolicy.evaluate": {
"total": 140.15450017800958,
"count": 18204,
"self": 140.15450017800958
}
}
},
"workers": {
"total": 0.2780344489847266,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 385.4978031010003,
"count": 18204,
"is_parallel": true,
"self": 221.39755651798578,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.05997420900007455,
"count": 1,
"is_parallel": true,
"self": 0.05892577700024049,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010484319998340652,
"count": 10,
"is_parallel": true,
"self": 0.0010484319998340652
}
}
},
"UnityEnvironment.step": {
"total": 0.023949594999976398,
"count": 1,
"is_parallel": true,
"self": 0.00030747899972993764,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001915770001232886,
"count": 1,
"is_parallel": true,
"self": 0.0001915770001232886
},
"communicator.exchange": {
"total": 0.022424301999990348,
"count": 1,
"is_parallel": true,
"self": 0.022424301999990348
},
"steps_from_proto": {
"total": 0.0010262370001328236,
"count": 1,
"is_parallel": true,
"self": 0.00024618800034659216,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007800489997862314,
"count": 10,
"is_parallel": true,
"self": 0.0007800489997862314
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 164.1002465830145,
"count": 18203,
"is_parallel": true,
"self": 7.187486544048397,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.23696453100024,
"count": 18203,
"is_parallel": true,
"self": 4.23696453100024
},
"communicator.exchange": {
"total": 129.32209929598662,
"count": 18203,
"is_parallel": true,
"self": 129.32209929598662
},
"steps_from_proto": {
"total": 23.35369621197924,
"count": 18203,
"is_parallel": true,
"self": 4.935631109949327,
"children": {
"_process_rank_one_or_two_observation": {
"total": 18.418065102029914,
"count": 182030,
"is_parallel": true,
"self": 18.418065102029914
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011642699996627925,
"count": 1,
"self": 0.00011642699996627925,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 381.7653120429836,
"count": 275342,
"is_parallel": true,
"self": 4.284401267018211,
"children": {
"process_trajectory": {
"total": 212.01779832196576,
"count": 275342,
"is_parallel": true,
"self": 211.42005949496593,
"children": {
"RLTrainer._checkpoint": {
"total": 0.59773882699983,
"count": 4,
"is_parallel": true,
"self": 0.59773882699983
}
}
},
"_update_policy": {
"total": 165.46311245399966,
"count": 90,
"is_parallel": true,
"self": 37.77223303501387,
"children": {
"TorchPPOOptimizer.update": {
"total": 127.69087941898579,
"count": 4587,
"is_parallel": true,
"self": 127.69087941898579
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08924547800006621,
"count": 1,
"self": 0.000626831000090533,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08861864699997568,
"count": 1,
"self": 0.08861864699997568
}
}
}
}
}
}
}