Jingwenwang's picture
First Push
da998bc verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9921086430549622,
"min": 0.9719911217689514,
"max": 2.863515615463257,
"count": 24
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10225.6640625,
"min": 9309.4443359375,
"max": 29325.263671875,
"count": 24
},
"SnowballTarget.Step.mean": {
"value": 239992.0,
"min": 9952.0,
"max": 239992.0,
"count": 24
},
"SnowballTarget.Step.sum": {
"value": 239992.0,
"min": 9952.0,
"max": 239992.0,
"count": 24
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.021932601928711,
"min": 0.3599489629268646,
"max": 13.021932601928711,
"count": 24
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2669.49609375,
"min": 69.8301010131836,
"max": 2669.49609375,
"count": 24
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 24
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 24
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07081195108921212,
"min": 0.05918560367495314,
"max": 0.07578525434512937,
"count": 24
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3540597554460606,
"min": 0.25729154885458927,
"max": 0.3768437800371983,
"count": 24
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18978086037963043,
"min": 0.08605398173790937,
"max": 0.2884049318000382,
"count": 24
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9489043018981521,
"min": 0.3442159269516375,
"max": 1.4420246590001908,
"count": 24
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 5.860098046666661e-06,
"min": 5.860098046666661e-06,
"max": 0.000293235002255,
"count": 24
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.9300490233333302e-05,
"min": 2.9300490233333302e-05,
"max": 0.0014043000318999998,
"count": 24
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10195333333333334,
"min": 0.10195333333333334,
"max": 0.19774500000000003,
"count": 24
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5097666666666667,
"min": 0.42431333333333343,
"max": 0.9681000000000001,
"count": 24
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00010747133333333324,
"min": 0.00010747133333333324,
"max": 0.0048874755,
"count": 24
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005373566666666662,
"min": 0.0005373566666666662,
"max": 0.023408189999999995,
"count": 24
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.745454545454546,
"min": 2.340909090909091,
"max": 25.745454545454546,
"count": 24
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1416.0,
"min": 103.0,
"max": 1416.0,
"count": 24
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.745454545454546,
"min": 2.340909090909091,
"max": 25.745454545454546,
"count": 24
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1416.0,
"min": 103.0,
"max": 1416.0,
"count": 24
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 24
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 24
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1711491198",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1711491732"
},
"total": 534.936081117,
"count": 1,
"self": 0.5501110600000629,
"children": {
"run_training.setup": {
"total": 0.05633390899998858,
"count": 1,
"self": 0.05633390899998858
},
"TrainerController.start_learning": {
"total": 534.329636148,
"count": 1,
"self": 0.7364119029945186,
"children": {
"TrainerController._reset_env": {
"total": 3.3836415239999837,
"count": 1,
"self": 3.3836415239999837
},
"TrainerController.advance": {
"total": 530.1041266310054,
"count": 21871,
"self": 0.3225722610105777,
"children": {
"env_step": {
"total": 529.7815543699949,
"count": 21871,
"self": 340.56061307698417,
"children": {
"SubprocessEnvManager._take_step": {
"total": 188.88176975900654,
"count": 21871,
"self": 1.7521579610032632,
"children": {
"TorchPolicy.evaluate": {
"total": 187.12961179800328,
"count": 21871,
"self": 187.12961179800328
}
}
},
"workers": {
"total": 0.33917153400415145,
"count": 21871,
"self": 0.0,
"children": {
"worker_root": {
"total": 532.8961890599902,
"count": 21871,
"is_parallel": true,
"self": 267.72580485198637,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.009420897000040895,
"count": 1,
"is_parallel": true,
"self": 0.004074342000080833,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0053465549999600626,
"count": 10,
"is_parallel": true,
"self": 0.0053465549999600626
}
}
},
"UnityEnvironment.step": {
"total": 0.041491468000003806,
"count": 1,
"is_parallel": true,
"self": 0.00064124999988735,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040665100004844135,
"count": 1,
"is_parallel": true,
"self": 0.00040665100004844135
},
"communicator.exchange": {
"total": 0.03853094500004772,
"count": 1,
"is_parallel": true,
"self": 0.03853094500004772
},
"steps_from_proto": {
"total": 0.001912622000020292,
"count": 1,
"is_parallel": true,
"self": 0.00038856400010445213,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00152405799991584,
"count": 10,
"is_parallel": true,
"self": 0.00152405799991584
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 265.17038420800384,
"count": 21870,
"is_parallel": true,
"self": 12.16091145201068,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.343227580998757,
"count": 21870,
"is_parallel": true,
"self": 6.343227580998757
},
"communicator.exchange": {
"total": 207.14814469899068,
"count": 21870,
"is_parallel": true,
"self": 207.14814469899068
},
"steps_from_proto": {
"total": 39.518100476003724,
"count": 21870,
"is_parallel": true,
"self": 7.455648249001399,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.062452227002325,
"count": 218700,
"is_parallel": true,
"self": 32.062452227002325
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00029559300003256794,
"count": 1,
"self": 0.00029559300003256794,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 523.4027591600392,
"count": 816410,
"is_parallel": true,
"self": 17.746344886093823,
"children": {
"process_trajectory": {
"total": 285.852697924946,
"count": 816410,
"is_parallel": true,
"self": 285.30148720694615,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5512107179998793,
"count": 4,
"is_parallel": true,
"self": 0.5512107179998793
}
}
},
"_update_policy": {
"total": 219.80371634899933,
"count": 109,
"is_parallel": true,
"self": 62.660682655001835,
"children": {
"TorchPPOOptimizer.update": {
"total": 157.1430336939975,
"count": 5556,
"is_parallel": true,
"self": 157.1430336939975
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1051604970000426,
"count": 1,
"self": 0.001131638000060775,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10402885899998182,
"count": 1,
"self": 0.10402885899998182
}
}
}
}
}
}
}