PHL99's picture
First Push
348af84
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.2313612699508667,
"min": 1.2313612699508667,
"max": 2.851682662963867,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 11919.5771484375,
"min": 11919.5771484375,
"max": 29298.1875,
"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": 12.65643310546875,
"min": 0.4628313183784485,
"max": 12.65643310546875,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2468.00439453125,
"min": 89.78927612304688,
"max": 2565.551025390625,
"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": 0.06788800884250021,
"min": 0.06431748992312636,
"max": 0.07364419996741288,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27155203537000083,
"min": 0.25726995969250543,
"max": 0.35905924586946714,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.15647529327353232,
"min": 0.12179020547887823,
"max": 0.2476928526864332,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6259011730941293,
"min": 0.4871608219155129,
"max": 1.238464263432166,
"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": 25.863636363636363,
"min": 3.977272727272727,
"max": 26.25,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1138.0,
"min": 175.0,
"max": 1432.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.57045409760692,
"min": 3.778409019112587,
"max": 24.93749955025586,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1081.0999802947044,
"min": 166.24999684095383,
"max": 1360.3999752998352,
"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": "1694721495",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1694722006"
},
"total": 511.065770465,
"count": 1,
"self": 0.7847481839996817,
"children": {
"run_training.setup": {
"total": 0.046187180000060835,
"count": 1,
"self": 0.046187180000060835
},
"TrainerController.start_learning": {
"total": 510.2348351010003,
"count": 1,
"self": 0.5522479760131773,
"children": {
"TrainerController._reset_env": {
"total": 4.335459738000054,
"count": 1,
"self": 4.335459738000054
},
"TrainerController.advance": {
"total": 504.99584295498676,
"count": 18246,
"self": 0.2697311609890676,
"children": {
"env_step": {
"total": 504.7261117939977,
"count": 18246,
"self": 357.1355518959783,
"children": {
"SubprocessEnvManager._take_step": {
"total": 147.31252992402074,
"count": 18246,
"self": 1.8118361479903342,
"children": {
"TorchPolicy.evaluate": {
"total": 145.5006937760304,
"count": 18246,
"self": 145.5006937760304
}
}
},
"workers": {
"total": 0.2780299739986276,
"count": 18246,
"self": 0.0,
"children": {
"worker_root": {
"total": 508.41856716701704,
"count": 18246,
"is_parallel": true,
"self": 256.20545058300786,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004600283999934618,
"count": 1,
"is_parallel": true,
"self": 0.0029352030001064122,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016650809998282057,
"count": 10,
"is_parallel": true,
"self": 0.0016650809998282057
}
}
},
"UnityEnvironment.step": {
"total": 0.058469410000043354,
"count": 1,
"is_parallel": true,
"self": 0.0005406270001913072,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00034087699987139786,
"count": 1,
"is_parallel": true,
"self": 0.00034087699987139786
},
"communicator.exchange": {
"total": 0.05430707200002871,
"count": 1,
"is_parallel": true,
"self": 0.05430707200002871
},
"steps_from_proto": {
"total": 0.0032808339999519376,
"count": 1,
"is_parallel": true,
"self": 0.00040847800005394674,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002872355999897991,
"count": 10,
"is_parallel": true,
"self": 0.002872355999897991
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 252.21311658400919,
"count": 18245,
"is_parallel": true,
"self": 10.924011936002444,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.373023851014523,
"count": 18245,
"is_parallel": true,
"self": 5.373023851014523
},
"communicator.exchange": {
"total": 198.68552432001866,
"count": 18245,
"is_parallel": true,
"self": 198.68552432001866
},
"steps_from_proto": {
"total": 37.23055647697356,
"count": 18245,
"is_parallel": true,
"self": 6.671831007933861,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.5587254690397,
"count": 182450,
"is_parallel": true,
"self": 30.5587254690397
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014247200033423724,
"count": 1,
"self": 0.00014247200033423724,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 501.3638524510361,
"count": 418027,
"is_parallel": true,
"self": 9.6731867931137,
"children": {
"process_trajectory": {
"total": 285.269587004924,
"count": 418027,
"is_parallel": true,
"self": 281.20580530592383,
"children": {
"RLTrainer._checkpoint": {
"total": 4.063781699000174,
"count": 4,
"is_parallel": true,
"self": 4.063781699000174
}
}
},
"_update_policy": {
"total": 206.4210786529984,
"count": 90,
"is_parallel": true,
"self": 78.7306870710031,
"children": {
"TorchPPOOptimizer.update": {
"total": 127.6903915819953,
"count": 4587,
"is_parallel": true,
"self": 127.6903915819953
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.3511419599999499,
"count": 1,
"self": 0.0008777010002631869,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3502642589996867,
"count": 1,
"self": 0.3502642589996867
}
}
}
}
}
}
}