Deisler's picture
the first model
2b11259
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8957509398460388,
"min": 0.8946871161460876,
"max": 2.8641250133514404,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8552.6298828125,
"min": 8552.6298828125,
"max": 29331.50390625,
"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": 13.179668426513672,
"min": 0.4105512499809265,
"max": 13.179668426513672,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2570.035400390625,
"min": 79.64694213867188,
"max": 2669.56884765625,
"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": 0.06392433745963454,
"min": 0.061778678963367153,
"max": 0.07762043769471347,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25569734983853815,
"min": 0.25569734983853815,
"max": 0.3881021884735673,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19089115275910087,
"min": 0.1523602128156698,
"max": 0.3044375975926717,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7635646110364035,
"min": 0.6094408512626792,
"max": 1.5221879879633584,
"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": 26.045454545454547,
"min": 4.181818181818182,
"max": 26.045454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1146.0,
"min": 184.0,
"max": 1411.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.045454545454547,
"min": 4.181818181818182,
"max": 26.045454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1146.0,
"min": 184.0,
"max": 1411.0,
"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": "1675442234",
"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": "1675442643"
},
"total": 408.75197856600005,
"count": 1,
"self": 0.38985530700017534,
"children": {
"run_training.setup": {
"total": 0.10100797999996303,
"count": 1,
"self": 0.10100797999996303
},
"TrainerController.start_learning": {
"total": 408.2611152789999,
"count": 1,
"self": 0.48409779300379796,
"children": {
"TrainerController._reset_env": {
"total": 9.463041184999952,
"count": 1,
"self": 9.463041184999952
},
"TrainerController.advance": {
"total": 398.1997918499959,
"count": 18200,
"self": 0.2447599740124815,
"children": {
"env_step": {
"total": 397.9550318759834,
"count": 18200,
"self": 261.039290329992,
"children": {
"SubprocessEnvManager._take_step": {
"total": 136.6675628199837,
"count": 18200,
"self": 1.3126174369870114,
"children": {
"TorchPolicy.evaluate": {
"total": 135.35494538299668,
"count": 18200,
"self": 30.2906013760047,
"children": {
"TorchPolicy.sample_actions": {
"total": 105.06434400699197,
"count": 18200,
"self": 105.06434400699197
}
}
}
}
},
"workers": {
"total": 0.24817872600772262,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 407.12918648397454,
"count": 18200,
"is_parallel": true,
"self": 195.61874287196486,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006672472999980528,
"count": 1,
"is_parallel": true,
"self": 0.002715582000064387,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003956890999916141,
"count": 10,
"is_parallel": true,
"self": 0.003956890999916141
}
}
},
"UnityEnvironment.step": {
"total": 0.03933171900007437,
"count": 1,
"is_parallel": true,
"self": 0.0004885939999894617,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022071600005801884,
"count": 1,
"is_parallel": true,
"self": 0.00022071600005801884
},
"communicator.exchange": {
"total": 0.036891787000058684,
"count": 1,
"is_parallel": true,
"self": 0.036891787000058684
},
"steps_from_proto": {
"total": 0.001730621999968207,
"count": 1,
"is_parallel": true,
"self": 0.0004040949997943244,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013265270001738827,
"count": 10,
"is_parallel": true,
"self": 0.0013265270001738827
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 211.51044361200968,
"count": 18199,
"is_parallel": true,
"self": 7.969187758984162,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.673285940008213,
"count": 18199,
"is_parallel": true,
"self": 4.673285940008213
},
"communicator.exchange": {
"total": 168.49759036300543,
"count": 18199,
"is_parallel": true,
"self": 168.49759036300543
},
"steps_from_proto": {
"total": 30.370379550011876,
"count": 18199,
"is_parallel": true,
"self": 6.054024827033686,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.31635472297819,
"count": 181990,
"is_parallel": true,
"self": 24.31635472297819
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.807000007327588e-05,
"count": 1,
"self": 3.807000007327588e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 395.5813992690156,
"count": 326093,
"is_parallel": true,
"self": 8.249636148019135,
"children": {
"process_trajectory": {
"total": 228.92614763899508,
"count": 326093,
"is_parallel": true,
"self": 228.30411060899507,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6220370300000013,
"count": 4,
"is_parallel": true,
"self": 0.6220370300000013
}
}
},
"_update_policy": {
"total": 158.4056154820014,
"count": 90,
"is_parallel": true,
"self": 38.10683232699898,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.29878315500241,
"count": 4587,
"is_parallel": true,
"self": 120.29878315500241
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11414638100018237,
"count": 1,
"self": 0.0008517850001226179,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11329459600005976,
"count": 1,
"self": 0.11329459600005976
}
}
}
}
}
}
}