software-vagabond's picture
First Push
92ee6fe
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8886485695838928,
"min": 0.8886485695838928,
"max": 2.8754658699035645,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8523.9169921875,
"min": 8523.9169921875,
"max": 29510.90625,
"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": 12.865021705627441,
"min": 0.30685538053512573,
"max": 12.918963432312012,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2508.67919921875,
"min": 59.52994155883789,
"max": 2635.468505859375,
"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": 0.0671614738523346,
"min": 0.059597669795003444,
"max": 0.0741984461004476,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2686458954093384,
"min": 0.23839067918001378,
"max": 0.36835690513401576,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20202662182204864,
"min": 0.10344703404196337,
"max": 0.29040580301308166,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8081064872881946,
"min": 0.4137881361678535,
"max": 1.397277724509146,
"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": 25.068181818181817,
"min": 3.0681818181818183,
"max": 25.5,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1103.0,
"min": 135.0,
"max": 1379.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.068181818181817,
"min": 3.0681818181818183,
"max": 25.5,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1103.0,
"min": 135.0,
"max": 1379.0,
"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": "1682953355",
"python_version": "3.9.5 (default, Jun 4 2021, 12:28:51) \n[GCC 7.5.0]",
"command_line_arguments": "/home/user/.virtualenvs/datascience/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=../training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
"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": "1682953783"
},
"total": 427.67076750000024,
"count": 1,
"self": 0.27024930000015956,
"children": {
"run_training.setup": {
"total": 0.03628359999993336,
"count": 1,
"self": 0.03628359999993336
},
"TrainerController.start_learning": {
"total": 427.36423460000015,
"count": 1,
"self": 0.4819087000505533,
"children": {
"TrainerController._reset_env": {
"total": 6.57483719999982,
"count": 1,
"self": 6.57483719999982
},
"TrainerController.advance": {
"total": 420.1345615999503,
"count": 18206,
"self": 0.2374139998478313,
"children": {
"env_step": {
"total": 419.89714760010247,
"count": 18206,
"self": 233.33821440007705,
"children": {
"SubprocessEnvManager._take_step": {
"total": 186.32833610007492,
"count": 18206,
"self": 1.5417443000542335,
"children": {
"TorchPolicy.evaluate": {
"total": 184.7865918000207,
"count": 18206,
"self": 184.7865918000207
}
}
},
"workers": {
"total": 0.2305970999505007,
"count": 18206,
"self": 0.0,
"children": {
"worker_root": {
"total": 426.369658099944,
"count": 18206,
"is_parallel": true,
"self": 283.5881347999739,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0015795999997862964,
"count": 1,
"is_parallel": true,
"self": 0.00048759999890535255,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010920000008809438,
"count": 10,
"is_parallel": true,
"self": 0.0010920000008809438
}
}
},
"UnityEnvironment.step": {
"total": 0.03227270000024873,
"count": 1,
"is_parallel": true,
"self": 0.0003040999999939231,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021530000003622263,
"count": 1,
"is_parallel": true,
"self": 0.00021530000003622263
},
"communicator.exchange": {
"total": 0.030107699999916804,
"count": 1,
"is_parallel": true,
"self": 0.030107699999916804
},
"steps_from_proto": {
"total": 0.0016456000003017834,
"count": 1,
"is_parallel": true,
"self": 0.0003581000000849599,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012875000002168235,
"count": 10,
"is_parallel": true,
"self": 0.0012875000002168235
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 142.7815232999701,
"count": 18205,
"is_parallel": true,
"self": 5.407041800119714,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.3258366999616555,
"count": 18205,
"is_parallel": true,
"self": 3.3258366999616555
},
"communicator.exchange": {
"total": 116.70700939994822,
"count": 18205,
"is_parallel": true,
"self": 116.70700939994822
},
"steps_from_proto": {
"total": 17.341635399940515,
"count": 18205,
"is_parallel": true,
"self": 3.947938299794714,
"children": {
"_process_rank_one_or_two_observation": {
"total": 13.3936971001458,
"count": 182050,
"is_parallel": true,
"self": 13.3936971001458
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.199999981821747e-05,
"count": 1,
"self": 7.199999981821747e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 417.953159599836,
"count": 306663,
"is_parallel": true,
"self": 6.507606099786244,
"children": {
"process_trajectory": {
"total": 221.06935910005086,
"count": 306663,
"is_parallel": true,
"self": 220.25168920005126,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8176698999996006,
"count": 4,
"is_parallel": true,
"self": 0.8176698999996006
}
}
},
"_update_policy": {
"total": 190.3761943999989,
"count": 90,
"is_parallel": true,
"self": 34.255864499965355,
"children": {
"TorchPPOOptimizer.update": {
"total": 156.12032990003354,
"count": 4587,
"is_parallel": true,
"self": 156.12032990003354
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.17285509999965143,
"count": 1,
"self": 0.004842899999857764,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16801219999979367,
"count": 1,
"self": 0.16801219999979367
}
}
}
}
}
}
}