jkorstad's picture
First Push
3456a54
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9476734399795532,
"min": 0.9476734399795532,
"max": 2.8778131008148193,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9048.3857421875,
"min": 9048.3857421875,
"max": 29566.65234375,
"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": 12.437761306762695,
"min": 0.19601501524448395,
"max": 12.437761306762695,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2425.363525390625,
"min": 38.026912689208984,
"max": 2517.46923828125,
"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": 0.062094177570257925,
"min": 0.061358542520525486,
"max": 0.07763073236599347,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2483767102810317,
"min": 0.2483767102810317,
"max": 0.3591660479016319,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22488581732499832,
"min": 0.09682733978272653,
"max": 0.2657777897137053,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8995432692999933,
"min": 0.38730935913090614,
"max": 1.3257739827329038,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 5.3880973060000045e-06,
"min": 5.3880973060000045e-06,
"max": 0.00019458800270600002,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.1552389224000018e-05,
"min": 2.1552389224000018e-05,
"max": 0.0009234400382800001,
"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": 24.204545454545453,
"min": 2.6818181818181817,
"max": 24.65909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1065.0,
"min": 118.0,
"max": 1342.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.204545454545453,
"min": 2.6818181818181817,
"max": 24.65909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1065.0,
"min": 118.0,
"max": 1342.0,
"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": "1681959509",
"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": "1681960007"
},
"total": 498.13083145300004,
"count": 1,
"self": 0.39419896399988374,
"children": {
"run_training.setup": {
"total": 0.11145799000007628,
"count": 1,
"self": 0.11145799000007628
},
"TrainerController.start_learning": {
"total": 497.6251744990001,
"count": 1,
"self": 0.5687576760047932,
"children": {
"TrainerController._reset_env": {
"total": 3.9015245550000373,
"count": 1,
"self": 3.9015245550000373
},
"TrainerController.advance": {
"total": 493.00401566299536,
"count": 18201,
"self": 0.3018667509776378,
"children": {
"env_step": {
"total": 492.7021489120177,
"count": 18201,
"self": 360.06516588504064,
"children": {
"SubprocessEnvManager._take_step": {
"total": 132.33904066298408,
"count": 18201,
"self": 1.8694378729821892,
"children": {
"TorchPolicy.evaluate": {
"total": 130.4696027900019,
"count": 18201,
"self": 130.4696027900019
}
}
},
"workers": {
"total": 0.2979423639930019,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 495.8643858420244,
"count": 18201,
"is_parallel": true,
"self": 229.26499531102195,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0072453049999694485,
"count": 1,
"is_parallel": true,
"self": 0.005463589999862961,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017817150001064874,
"count": 10,
"is_parallel": true,
"self": 0.0017817150001064874
}
}
},
"UnityEnvironment.step": {
"total": 0.03837965900004292,
"count": 1,
"is_parallel": true,
"self": 0.0006007939999790324,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003466780000280778,
"count": 1,
"is_parallel": true,
"self": 0.0003466780000280778
},
"communicator.exchange": {
"total": 0.03543650599999637,
"count": 1,
"is_parallel": true,
"self": 0.03543650599999637
},
"steps_from_proto": {
"total": 0.00199568100003944,
"count": 1,
"is_parallel": true,
"self": 0.0004473550000057003,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015483260000337395,
"count": 10,
"is_parallel": true,
"self": 0.0015483260000337395
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 266.5993905310024,
"count": 18200,
"is_parallel": true,
"self": 10.62130000403522,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.241740079996362,
"count": 18200,
"is_parallel": true,
"self": 6.241740079996362
},
"communicator.exchange": {
"total": 213.5028830649676,
"count": 18200,
"is_parallel": true,
"self": 213.5028830649676
},
"steps_from_proto": {
"total": 36.233467382003255,
"count": 18200,
"is_parallel": true,
"self": 7.405323017034334,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.82814436496892,
"count": 182000,
"is_parallel": true,
"self": 28.82814436496892
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012051899989273807,
"count": 1,
"self": 0.00012051899989273807,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 488.9379592179532,
"count": 440436,
"is_parallel": true,
"self": 11.233793909039377,
"children": {
"process_trajectory": {
"total": 269.91965510291357,
"count": 440436,
"is_parallel": true,
"self": 269.0492367389136,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8704183639999883,
"count": 4,
"is_parallel": true,
"self": 0.8704183639999883
}
}
},
"_update_policy": {
"total": 207.78451020600028,
"count": 90,
"is_parallel": true,
"self": 78.62929944199902,
"children": {
"TorchPPOOptimizer.update": {
"total": 129.15521076400125,
"count": 4587,
"is_parallel": true,
"self": 129.15521076400125
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15075608600000123,
"count": 1,
"self": 0.0008708240000032674,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14988526199999797,
"count": 1,
"self": 0.14988526199999797
}
}
}
}
}
}
}