Gleb1441's picture
First Push
18f67c5 verified
Raw
History Blame Contribute Delete
18.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.5145233869552612,
"min": 0.5145233869552612,
"max": 2.8660833835601807,
"count": 70
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 5631.45849609375,
"min": 4595.94921875,
"max": 31747.60546875,
"count": 70
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 70
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 70
},
"SnowballTarget.Step.mean": {
"value": 699800.0,
"min": 9800.0,
"max": 699800.0,
"count": 70
},
"SnowballTarget.Step.sum": {
"value": 699800.0,
"min": 9800.0,
"max": 699800.0,
"count": 70
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 14.108232498168945,
"min": 0.3773690462112427,
"max": 14.246672630310059,
"count": 70
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 705.41162109375,
"min": 18.4910831451416,
"max": 712.3336181640625,
"count": 70
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.68,
"min": 2.7755102040816326,
"max": 28.4,
"count": 70
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1384.0,
"min": 136.0,
"max": 1420.0,
"count": 70
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.68,
"min": 2.7755102040816326,
"max": 28.4,
"count": 70
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1384.0,
"min": 136.0,
"max": 1420.0,
"count": 70
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.043044207071943674,
"min": 0.034920364098430426,
"max": 0.05579220969617989,
"count": 70
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.21522103535971837,
"min": 0.1396814563937217,
"max": 0.2789610484808994,
"count": 70
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17004195228219032,
"min": 0.11393281910568476,
"max": 0.31102832704782485,
"count": 70
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8502097614109516,
"min": 0.45573127642273903,
"max": 1.5551416352391243,
"count": 70
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 6.857242171428565e-06,
"min": 6.857242171428565e-06,
"max": 0.0009921428579285714,
"count": 70
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.4286210857142825e-05,
"min": 3.4286210857142825e-05,
"max": 0.004890000011000001,
"count": 70
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1006857142857143,
"min": 0.1006857142857143,
"max": 0.19921428571428576,
"count": 70
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5034285714285714,
"min": 0.40840000000000004,
"max": 0.989,
"count": 70
},
"SnowballTarget.Policy.Beta.mean": {
"value": 4.421714285714282e-05,
"min": 4.421714285714282e-05,
"max": 0.004960792857142858,
"count": 70
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00022108571428571411,
"min": 0.00022108571428571411,
"max": 0.0244511,
"count": 70
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 70
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 70
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1781589939",
"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 --force",
"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": "1781591777"
},
"total": 1837.4215608340005,
"count": 1,
"self": 0.47631639199971687,
"children": {
"run_training.setup": {
"total": 0.02647557400041478,
"count": 1,
"self": 0.02647557400041478
},
"TrainerController.start_learning": {
"total": 1836.9187688680004,
"count": 1,
"self": 2.3825179219866186,
"children": {
"TrainerController._reset_env": {
"total": 2.6619302489998518,
"count": 1,
"self": 2.6619302489998518
},
"TrainerController.advance": {
"total": 1831.7934550390146,
"count": 63807,
"self": 1.0248483731356828,
"children": {
"env_step": {
"total": 1830.768606665879,
"count": 63807,
"self": 1131.8993143629723,
"children": {
"SubprocessEnvManager._take_step": {
"total": 697.8171795669773,
"count": 63807,
"self": 5.611469959815167,
"children": {
"TorchPolicy.evaluate": {
"total": 692.2057096071621,
"count": 63807,
"self": 692.2057096071621
}
}
},
"workers": {
"total": 1.0521127359293132,
"count": 63807,
"self": 0.0,
"children": {
"worker_root": {
"total": 1830.7343053119612,
"count": 63807,
"is_parallel": true,
"self": 867.667243464914,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002205762999892613,
"count": 1,
"is_parallel": true,
"self": 0.0006677570004285371,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001538005999464076,
"count": 10,
"is_parallel": true,
"self": 0.001538005999464076
}
}
},
"UnityEnvironment.step": {
"total": 0.08324944500009224,
"count": 1,
"is_parallel": true,
"self": 0.0006333189999168098,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044682499992632074,
"count": 1,
"is_parallel": true,
"self": 0.00044682499992632074
},
"communicator.exchange": {
"total": 0.07878374400024768,
"count": 1,
"is_parallel": true,
"self": 0.07878374400024768
},
"steps_from_proto": {
"total": 0.003385557000001427,
"count": 1,
"is_parallel": true,
"self": 0.0004515180012276687,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002934038998773758,
"count": 10,
"is_parallel": true,
"self": 0.002934038998773758
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 963.0670618470472,
"count": 63806,
"is_parallel": true,
"self": 41.00977993215247,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.309366140884322,
"count": 63806,
"is_parallel": true,
"self": 21.309366140884322
},
"communicator.exchange": {
"total": 745.3081576158988,
"count": 63806,
"is_parallel": true,
"self": 745.3081576158988
},
"steps_from_proto": {
"total": 155.43975815811154,
"count": 63806,
"is_parallel": true,
"self": 29.699138919318557,
"children": {
"_process_rank_one_or_two_observation": {
"total": 125.74061923879299,
"count": 638060,
"is_parallel": true,
"self": 125.74061923879299
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0012713669993900112,
"count": 1,
"self": 0.0012713669993900112,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1810.8553188466021,
"count": 2360083,
"is_parallel": true,
"self": 56.025633100267896,
"children": {
"process_trajectory": {
"total": 1128.9643205633292,
"count": 2360083,
"is_parallel": true,
"self": 1126.9115021663297,
"children": {
"RLTrainer._checkpoint": {
"total": 2.0528183969995553,
"count": 14,
"is_parallel": true,
"self": 2.0528183969995553
}
}
},
"_update_policy": {
"total": 625.865365183005,
"count": 318,
"is_parallel": true,
"self": 183.00152960402602,
"children": {
"TorchPPOOptimizer.update": {
"total": 442.863835578979,
"count": 7632,
"is_parallel": true,
"self": 442.863835578979
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.07959429099992121,
"count": 1,
"self": 0.0010057780000352068,
"children": {
"RLTrainer._checkpoint": {
"total": 0.078588512999886,
"count": 1,
"self": 0.078588512999886
}
}
}
}
}
}
}