akoshel's picture
first push
3f3d1a1
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0500288009643555,
"min": 1.0500288009643555,
"max": 2.8516523838043213,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10060.326171875,
"min": 10060.326171875,
"max": 29266.5078125,
"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": 13.16783332824707,
"min": 0.5422272086143494,
"max": 13.16783332824707,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2567.7275390625,
"min": 105.19207763671875,
"max": 2668.236572265625,
"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": 0.06967519198110049,
"min": 0.06283444013462548,
"max": 0.07232733431623738,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27870076792440196,
"min": 0.2647826534622236,
"max": 0.3616350784260944,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1977041307106322,
"min": 0.13670407882640503,
"max": 0.28467851094171115,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7908165228425288,
"min": 0.5468163153056201,
"max": 1.4233925547085557,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.347009730600001e-05,
"min": 1.347009730600001e-05,
"max": 0.00048647000270600005,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.388038922400004e-05,
"min": 5.388038922400004e-05,
"max": 0.00230860003828,
"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": 25.477272727272727,
"min": 4.25,
"max": 26.236363636363638,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1121.0,
"min": 187.0,
"max": 1443.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.477272727272727,
"min": 4.25,
"max": 26.236363636363638,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1121.0,
"min": 187.0,
"max": 1443.0,
"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": "1676815341",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1676815787"
},
"total": 446.380338531,
"count": 1,
"self": 0.3933090299999549,
"children": {
"run_training.setup": {
"total": 0.11161121400004959,
"count": 1,
"self": 0.11161121400004959
},
"TrainerController.start_learning": {
"total": 445.875418287,
"count": 1,
"self": 0.5576627209819662,
"children": {
"TrainerController._reset_env": {
"total": 9.516426995000074,
"count": 1,
"self": 9.516426995000074
},
"TrainerController.advance": {
"total": 435.68525835501794,
"count": 18213,
"self": 0.2725959340108375,
"children": {
"env_step": {
"total": 435.4126624210071,
"count": 18213,
"self": 296.9583107380239,
"children": {
"SubprocessEnvManager._take_step": {
"total": 138.19038152499206,
"count": 18213,
"self": 1.4339624779905762,
"children": {
"TorchPolicy.evaluate": {
"total": 136.7564190470015,
"count": 18213,
"self": 30.0831368239958,
"children": {
"TorchPolicy.sample_actions": {
"total": 106.67328222300569,
"count": 18213,
"self": 106.67328222300569
}
}
}
}
},
"workers": {
"total": 0.2639701579911389,
"count": 18213,
"self": 0.0,
"children": {
"worker_root": {
"total": 444.4395309609969,
"count": 18213,
"is_parallel": true,
"self": 217.69024398598754,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0061614150000650625,
"count": 1,
"is_parallel": true,
"self": 0.0035877679997611267,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002573647000303936,
"count": 10,
"is_parallel": true,
"self": 0.002573647000303936
}
}
},
"UnityEnvironment.step": {
"total": 0.03335055900004136,
"count": 1,
"is_parallel": true,
"self": 0.00040479400001913746,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00032242700001461344,
"count": 1,
"is_parallel": true,
"self": 0.00032242700001461344
},
"communicator.exchange": {
"total": 0.03126054699998804,
"count": 1,
"is_parallel": true,
"self": 0.03126054699998804
},
"steps_from_proto": {
"total": 0.0013627910000195698,
"count": 1,
"is_parallel": true,
"self": 0.0003475890002846427,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001015201999734927,
"count": 10,
"is_parallel": true,
"self": 0.001015201999734927
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 226.74928697500934,
"count": 18212,
"is_parallel": true,
"self": 9.10678838701881,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.979899002010143,
"count": 18212,
"is_parallel": true,
"self": 4.979899002010143
},
"communicator.exchange": {
"total": 182.85178069499034,
"count": 18212,
"is_parallel": true,
"self": 182.85178069499034
},
"steps_from_proto": {
"total": 29.81081889099005,
"count": 18212,
"is_parallel": true,
"self": 6.468950036971023,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.341868854019026,
"count": 182120,
"is_parallel": true,
"self": 23.341868854019026
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011760000006688642,
"count": 1,
"self": 0.00011760000006688642,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 432.6170286749684,
"count": 384388,
"is_parallel": true,
"self": 9.322115119914656,
"children": {
"process_trajectory": {
"total": 245.8703067340531,
"count": 384388,
"is_parallel": true,
"self": 244.9230301330531,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9472766009999987,
"count": 4,
"is_parallel": true,
"self": 0.9472766009999987
}
}
},
"_update_policy": {
"total": 177.42460682100068,
"count": 90,
"is_parallel": true,
"self": 61.787244394000254,
"children": {
"TorchPPOOptimizer.update": {
"total": 115.63736242700043,
"count": 4587,
"is_parallel": true,
"self": 115.63736242700043
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11595261599995865,
"count": 1,
"self": 0.0008488190001116891,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11510379699984696,
"count": 1,
"self": 0.11510379699984696
}
}
}
}
}
}
}