thomas2112's picture
First Push
d8f263f
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0395679473876953,
"min": 1.0395679473876953,
"max": 2.868809461593628,
"count": 21
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10669.0859375,
"min": 10045.697265625,
"max": 29442.591796875,
"count": 21
},
"SnowballTarget.Step.mean": {
"value": 209960.0,
"min": 9952.0,
"max": 209960.0,
"count": 21
},
"SnowballTarget.Step.sum": {
"value": 209960.0,
"min": 9952.0,
"max": 209960.0,
"count": 21
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.271980285644531,
"min": 0.42478081583976746,
"max": 13.448873519897461,
"count": 21
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2707.48388671875,
"min": 82.40747833251953,
"max": 2737.65673828125,
"count": 21
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 21
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 21
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06335745896635048,
"min": 0.062573816038796,
"max": 0.07361110987138306,
"count": 21
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3167872948317524,
"min": 0.2523695758849784,
"max": 0.36805554935691526,
"count": 21
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20330669643247828,
"min": 0.0939762758977903,
"max": 0.28740696053878934,
"count": 21
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.0165334821623915,
"min": 0.3759051035911612,
"max": 1.3639594643723731,
"count": 21
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 0.0002693232102255999,
"min": 0.0002693232102255999,
"max": 0.00029918820027059994,
"count": 21
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.0013466160511279995,
"min": 0.0010832328389224,
"max": 0.0014885160038279998,
"count": 21
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.18977439999999998,
"min": 0.18977439999999998,
"max": 0.1997294,
"count": 21
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.9488719999999999,
"min": 0.7610776,
"max": 0.996172,
"count": 21
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00448974256,
"min": 0.00448974256,
"max": 0.004986497059999999,
"count": 21
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0224487128,
"min": 0.018057772240000002,
"max": 0.024808982800000004,
"count": 21
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.672727272727272,
"min": 2.9318181818181817,
"max": 26.40909090909091,
"count": 21
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1412.0,
"min": 129.0,
"max": 1445.0,
"count": 21
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.672727272727272,
"min": 2.9318181818181817,
"max": 26.40909090909091,
"count": 21
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1412.0,
"min": 129.0,
"max": 1445.0,
"count": 21
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 21
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 21
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1689241923",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1689242477"
},
"total": 554.276952676,
"count": 1,
"self": 0.3117098040000883,
"children": {
"run_training.setup": {
"total": 0.04162643099999741,
"count": 1,
"self": 0.04162643099999741
},
"TrainerController.start_learning": {
"total": 553.9236164409999,
"count": 1,
"self": 0.7854480689965158,
"children": {
"TrainerController._reset_env": {
"total": 4.060071845999971,
"count": 1,
"self": 4.060071845999971
},
"TrainerController.advance": {
"total": 548.6239091180036,
"count": 19872,
"self": 0.33984936999399906,
"children": {
"env_step": {
"total": 548.2840597480096,
"count": 19872,
"self": 399.4344885000111,
"children": {
"SubprocessEnvManager._take_step": {
"total": 148.50437248800142,
"count": 19872,
"self": 2.050315719995808,
"children": {
"TorchPolicy.evaluate": {
"total": 146.45405676800561,
"count": 19872,
"self": 146.45405676800561
}
}
},
"workers": {
"total": 0.3451987599970039,
"count": 19871,
"self": 0.0,
"children": {
"worker_root": {
"total": 551.6497738500044,
"count": 19871,
"is_parallel": true,
"self": 256.9445622100087,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005598484999950415,
"count": 1,
"is_parallel": true,
"self": 0.0039698189999626265,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016286659999877884,
"count": 10,
"is_parallel": true,
"self": 0.0016286659999877884
}
}
},
"UnityEnvironment.step": {
"total": 0.061808578000011494,
"count": 1,
"is_parallel": true,
"self": 0.0007043360000125176,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003453340000305616,
"count": 1,
"is_parallel": true,
"self": 0.0003453340000305616
},
"communicator.exchange": {
"total": 0.0583374029999959,
"count": 1,
"is_parallel": true,
"self": 0.0583374029999959
},
"steps_from_proto": {
"total": 0.0024215049999725125,
"count": 1,
"is_parallel": true,
"self": 0.0004542980000223906,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001967206999950122,
"count": 10,
"is_parallel": true,
"self": 0.001967206999950122
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 294.7052116399957,
"count": 19870,
"is_parallel": true,
"self": 12.26876081499205,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.389486314004671,
"count": 19870,
"is_parallel": true,
"self": 6.389486314004671
},
"communicator.exchange": {
"total": 232.5423844440029,
"count": 19870,
"is_parallel": true,
"self": 232.5423844440029
},
"steps_from_proto": {
"total": 43.504580066996084,
"count": 19870,
"is_parallel": true,
"self": 7.923354678982776,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.58122538801331,
"count": 198700,
"is_parallel": true,
"self": 35.58122538801331
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012839299995448528,
"count": 1,
"self": 0.00012839299995448528,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 544.462519772013,
"count": 513158,
"is_parallel": true,
"self": 11.73783568803924,
"children": {
"process_trajectory": {
"total": 300.2297592249733,
"count": 513158,
"is_parallel": true,
"self": 298.4607747529734,
"children": {
"RLTrainer._checkpoint": {
"total": 1.768984471999886,
"count": 4,
"is_parallel": true,
"self": 1.768984471999886
}
}
},
"_update_policy": {
"total": 232.4949248590005,
"count": 99,
"is_parallel": true,
"self": 86.91457645400322,
"children": {
"TorchPPOOptimizer.update": {
"total": 145.58034840499727,
"count": 5046,
"is_parallel": true,
"self": 145.58034840499727
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.45405901499998436,
"count": 1,
"self": 0.001201840000021548,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4528571749999628,
"count": 1,
"self": 0.4528571749999628
}
}
}
}
}
}
}