SaNsOT's picture
Initial commit
7935220 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8509840965270996,
"min": 0.8509840965270996,
"max": 2.869584083557129,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8143.91796875,
"min": 8143.91796875,
"max": 29418.9765625,
"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": 12.851890563964844,
"min": 0.44836685061454773,
"max": 12.851890563964844,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2506.11865234375,
"min": 86.98316955566406,
"max": 2588.6494140625,
"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": 0.07301209376515437,
"min": 0.06473684797917181,
"max": 0.07345509141348028,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2920483750606175,
"min": 0.2666821647058789,
"max": 0.3672754570674014,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18013897494358175,
"min": 0.14015655758603496,
"max": 0.2899574300984412,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.720555899774327,
"min": 0.5606262303441398,
"max": 1.449787150492206,
"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": 25.84090909090909,
"min": 3.7954545454545454,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1137.0,
"min": 167.0,
"max": 1401.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.84090909090909,
"min": 3.7954545454545454,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1137.0,
"min": 167.0,
"max": 1401.0,
"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": "1750240336",
"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",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1750240870"
},
"total": 534.2941667919999,
"count": 1,
"self": 0.48780873400005476,
"children": {
"run_training.setup": {
"total": 0.040778791999969144,
"count": 1,
"self": 0.040778791999969144
},
"TrainerController.start_learning": {
"total": 533.7655792659999,
"count": 1,
"self": 0.7982639960110873,
"children": {
"TrainerController._reset_env": {
"total": 4.377336053000022,
"count": 1,
"self": 4.377336053000022
},
"TrainerController.advance": {
"total": 528.5145716159888,
"count": 18203,
"self": 0.4200327899789045,
"children": {
"env_step": {
"total": 528.0945388260099,
"count": 18203,
"self": 413.6211331629962,
"children": {
"SubprocessEnvManager._take_step": {
"total": 114.09760095401157,
"count": 18203,
"self": 1.8887501610214485,
"children": {
"TorchPolicy.evaluate": {
"total": 112.20885079299012,
"count": 18203,
"self": 112.20885079299012
}
}
},
"workers": {
"total": 0.3758047090020682,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 531.765054461029,
"count": 18203,
"is_parallel": true,
"self": 242.7388381950343,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008956133999959093,
"count": 1,
"is_parallel": true,
"self": 0.006266842000059114,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0026892919998999787,
"count": 10,
"is_parallel": true,
"self": 0.0026892919998999787
}
}
},
"UnityEnvironment.step": {
"total": 0.1180696500000522,
"count": 1,
"is_parallel": true,
"self": 0.0008095169999933205,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003953100000444465,
"count": 1,
"is_parallel": true,
"self": 0.0003953100000444465
},
"communicator.exchange": {
"total": 0.11289679300000444,
"count": 1,
"is_parallel": true,
"self": 0.11289679300000444
},
"steps_from_proto": {
"total": 0.003968030000010003,
"count": 1,
"is_parallel": true,
"self": 0.0005295990001741302,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003438430999835873,
"count": 10,
"is_parallel": true,
"self": 0.003438430999835873
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 289.02621626599466,
"count": 18202,
"is_parallel": true,
"self": 12.857992812971702,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.661437087024183,
"count": 18202,
"is_parallel": true,
"self": 6.661437087024183
},
"communicator.exchange": {
"total": 228.21812284599173,
"count": 18202,
"is_parallel": true,
"self": 228.21812284599173
},
"steps_from_proto": {
"total": 41.28866352000705,
"count": 18202,
"is_parallel": true,
"self": 8.173074563966452,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.1155889560406,
"count": 182020,
"is_parallel": true,
"self": 33.1155889560406
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016455099989798327,
"count": 1,
"self": 0.00016455099989798327,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 522.5530220270235,
"count": 752779,
"is_parallel": true,
"self": 15.648133566037131,
"children": {
"process_trajectory": {
"total": 283.12167726398604,
"count": 752779,
"is_parallel": true,
"self": 282.44022527998584,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6814519840002049,
"count": 4,
"is_parallel": true,
"self": 0.6814519840002049
}
}
},
"_update_policy": {
"total": 223.78321119700036,
"count": 90,
"is_parallel": true,
"self": 61.95024702200408,
"children": {
"TorchPPOOptimizer.update": {
"total": 161.83296417499628,
"count": 4587,
"is_parallel": true,
"self": 161.83296417499628
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.07524305000015374,
"count": 1,
"self": 0.0010578950000308396,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0741851550001229,
"count": 1,
"self": 0.0741851550001229
}
}
}
}
}
}
}