dhorbach's picture
First Push
22ecab2
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9623980522155762,
"min": 0.9623980522155762,
"max": 2.8696062564849854,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9188.9765625,
"min": 9188.9765625,
"max": 29387.638671875,
"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": 12.872698783874512,
"min": 0.3955494165420532,
"max": 12.872698783874512,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2510.17626953125,
"min": 76.73658752441406,
"max": 2615.4462890625,
"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": 0.06537666144397329,
"min": 0.0646682668310663,
"max": 0.0741013137865629,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26150664577589317,
"min": 0.26150664577589317,
"max": 0.37050656893281453,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20715870752054102,
"min": 0.16686021006556556,
"max": 0.2965134691958334,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8286348300821641,
"min": 0.6674408402622622,
"max": 1.3732696549565184,
"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": 25.204545454545453,
"min": 4.181818181818182,
"max": 25.490909090909092,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1109.0,
"min": 184.0,
"max": 1402.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.204545454545453,
"min": 4.181818181818182,
"max": 25.490909090909092,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1109.0,
"min": 184.0,
"max": 1402.0,
"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": "1681814583",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1681815020"
},
"total": 437.31025462699995,
"count": 1,
"self": 0.3802455459999692,
"children": {
"run_training.setup": {
"total": 0.11486107700000048,
"count": 1,
"self": 0.11486107700000048
},
"TrainerController.start_learning": {
"total": 436.815148004,
"count": 1,
"self": 0.5221470819964225,
"children": {
"TrainerController._reset_env": {
"total": 4.791255569999976,
"count": 1,
"self": 4.791255569999976
},
"TrainerController.advance": {
"total": 431.3756140270035,
"count": 18214,
"self": 0.25030662401002246,
"children": {
"env_step": {
"total": 431.1253074029935,
"count": 18214,
"self": 316.17188275399945,
"children": {
"SubprocessEnvManager._take_step": {
"total": 114.70533122499677,
"count": 18214,
"self": 1.6383236429929298,
"children": {
"TorchPolicy.evaluate": {
"total": 113.06700758200384,
"count": 18214,
"self": 113.06700758200384
}
}
},
"workers": {
"total": 0.2480934239972612,
"count": 18214,
"self": 0.0,
"children": {
"worker_root": {
"total": 435.4062290090004,
"count": 18214,
"is_parallel": true,
"self": 202.2333980530007,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004666249000024436,
"count": 1,
"is_parallel": true,
"self": 0.0031854270000053475,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014808220000190886,
"count": 10,
"is_parallel": true,
"self": 0.0014808220000190886
}
}
},
"UnityEnvironment.step": {
"total": 0.06525853900001266,
"count": 1,
"is_parallel": true,
"self": 0.0005716100000654478,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004592249999859632,
"count": 1,
"is_parallel": true,
"self": 0.0004592249999859632
},
"communicator.exchange": {
"total": 0.062346300999990945,
"count": 1,
"is_parallel": true,
"self": 0.062346300999990945
},
"steps_from_proto": {
"total": 0.0018814029999703052,
"count": 1,
"is_parallel": true,
"self": 0.0003776749999246931,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015037280000456121,
"count": 10,
"is_parallel": true,
"self": 0.0015037280000456121
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 233.1728309559997,
"count": 18213,
"is_parallel": true,
"self": 9.590276285996254,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.2515953330004095,
"count": 18213,
"is_parallel": true,
"self": 5.2515953330004095
},
"communicator.exchange": {
"total": 187.90069758100526,
"count": 18213,
"is_parallel": true,
"self": 187.90069758100526
},
"steps_from_proto": {
"total": 30.430261755997776,
"count": 18213,
"is_parallel": true,
"self": 5.906780009009367,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.52348174698841,
"count": 182130,
"is_parallel": true,
"self": 24.52348174698841
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010522500008391944,
"count": 1,
"self": 0.00010522500008391944,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 428.12816247502025,
"count": 390957,
"is_parallel": true,
"self": 9.535700958986581,
"children": {
"process_trajectory": {
"total": 236.3148491730343,
"count": 390957,
"is_parallel": true,
"self": 234.98691083703437,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3279383359999315,
"count": 4,
"is_parallel": true,
"self": 1.3279383359999315
}
}
},
"_update_policy": {
"total": 182.27761234299936,
"count": 90,
"is_parallel": true,
"self": 66.2863572869968,
"children": {
"TorchPPOOptimizer.update": {
"total": 115.99125505600256,
"count": 4587,
"is_parallel": true,
"self": 115.99125505600256
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12602609999999004,
"count": 1,
"self": 0.0009401780000644067,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12508592199992563,
"count": 1,
"self": 0.12508592199992563
}
}
}
}
}
}
}