maxkskhor's picture
First Push
e489625
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0329939126968384,
"min": 1.0232270956039429,
"max": 2.8680527210235596,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9874.388671875,
"min": 9874.388671875,
"max": 29403.275390625,
"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": 12.859114646911621,
"min": 0.3769174814224243,
"max": 12.859114646911621,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2507.52734375,
"min": 73.12199401855469,
"max": 2617.170654296875,
"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": 0.07234799983116853,
"min": 0.06588580384764903,
"max": 0.07773147028067387,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28939199932467413,
"min": 0.2638012878262945,
"max": 0.3886573514033693,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20139911274115246,
"min": 0.12935352758458796,
"max": 0.28445627005661234,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8055964509646099,
"min": 0.5174141103383518,
"max": 1.4222813502830618,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"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": 25.15909090909091,
"min": 3.522727272727273,
"max": 25.431818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1107.0,
"min": 155.0,
"max": 1385.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.15909090909091,
"min": 3.522727272727273,
"max": 25.431818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1107.0,
"min": 155.0,
"max": 1385.0,
"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": "1688640382",
"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": "1688640860"
},
"total": 478.32513953399996,
"count": 1,
"self": 0.44099060199994256,
"children": {
"run_training.setup": {
"total": 0.04209900400007882,
"count": 1,
"self": 0.04209900400007882
},
"TrainerController.start_learning": {
"total": 477.84204992799994,
"count": 1,
"self": 0.5174447199982524,
"children": {
"TrainerController._reset_env": {
"total": 4.904096197000058,
"count": 1,
"self": 4.904096197000058
},
"TrainerController.advance": {
"total": 472.27450875100146,
"count": 18202,
"self": 0.26771179799357014,
"children": {
"env_step": {
"total": 472.0067969530079,
"count": 18202,
"self": 340.67004786499615,
"children": {
"SubprocessEnvManager._take_step": {
"total": 131.07378102699954,
"count": 18202,
"self": 1.9254259819870185,
"children": {
"TorchPolicy.evaluate": {
"total": 129.14835504501252,
"count": 18202,
"self": 129.14835504501252
}
}
},
"workers": {
"total": 0.26296806101220227,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 476.1997429920077,
"count": 18202,
"is_parallel": true,
"self": 223.55765708901413,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005128297999931419,
"count": 1,
"is_parallel": true,
"self": 0.0035939309998411773,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001534367000090242,
"count": 10,
"is_parallel": true,
"self": 0.001534367000090242
}
}
},
"UnityEnvironment.step": {
"total": 0.06872302800002217,
"count": 1,
"is_parallel": true,
"self": 0.0006957409999586162,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046430099996541685,
"count": 1,
"is_parallel": true,
"self": 0.00046430099996541685
},
"communicator.exchange": {
"total": 0.06521843000007266,
"count": 1,
"is_parallel": true,
"self": 0.06521843000007266
},
"steps_from_proto": {
"total": 0.0023445560000254773,
"count": 1,
"is_parallel": true,
"self": 0.0004272529998843311,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019173030001411462,
"count": 10,
"is_parallel": true,
"self": 0.0019173030001411462
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 252.64208590299359,
"count": 18201,
"is_parallel": true,
"self": 10.706306206985914,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.51509861400632,
"count": 18201,
"is_parallel": true,
"self": 5.51509861400632
},
"communicator.exchange": {
"total": 198.6318065150042,
"count": 18201,
"is_parallel": true,
"self": 198.6318065150042
},
"steps_from_proto": {
"total": 37.78887456699715,
"count": 18201,
"is_parallel": true,
"self": 6.667965773005449,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.120908793991703,
"count": 182010,
"is_parallel": true,
"self": 31.120908793991703
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011139800017190282,
"count": 1,
"self": 0.00011139800017190282,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 468.46847012597254,
"count": 466678,
"is_parallel": true,
"self": 10.03799078794998,
"children": {
"process_trajectory": {
"total": 256.9181383740223,
"count": 466678,
"is_parallel": true,
"self": 256.12166110202236,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7964772719999473,
"count": 4,
"is_parallel": true,
"self": 0.7964772719999473
}
}
},
"_update_policy": {
"total": 201.51234096400026,
"count": 90,
"is_parallel": true,
"self": 80.64706181599615,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.8652791480041,
"count": 4587,
"is_parallel": true,
"self": 120.8652791480041
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14588886199999251,
"count": 1,
"self": 0.0008763759999510512,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14501248600004146,
"count": 1,
"self": 0.14501248600004146
}
}
}
}
}
}
}