eugene-d's picture
Initial commit
25831d6
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8990530967712402,
"min": 0.8990530967712402,
"max": 2.862276077270508,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8584.1591796875,
"min": 8584.1591796875,
"max": 29312.5703125,
"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": 12.921759605407715,
"min": 0.4083092212677002,
"max": 12.921759605407715,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2519.7431640625,
"min": 79.21199035644531,
"max": 2620.24560546875,
"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": 0.0675197505995896,
"min": 0.06264982174707615,
"max": 0.07775072566308903,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2700790023983584,
"min": 0.256016352132885,
"max": 0.36125268499645424,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19330023565128737,
"min": 0.11062940215924756,
"max": 0.2847083871271096,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7732009426051495,
"min": 0.44251760863699025,
"max": 1.3294197867314022,
"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": 25.431818181818183,
"min": 3.5454545454545454,
"max": 25.431818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1119.0,
"min": 156.0,
"max": 1393.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.431818181818183,
"min": 3.5454545454545454,
"max": 25.431818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1119.0,
"min": 156.0,
"max": 1393.0,
"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": "1676889192",
"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": "1676889641"
},
"total": 448.784668741,
"count": 1,
"self": 0.4365946040001063,
"children": {
"run_training.setup": {
"total": 0.11234716499996011,
"count": 1,
"self": 0.11234716499996011
},
"TrainerController.start_learning": {
"total": 448.23572697199995,
"count": 1,
"self": 0.5041037350038664,
"children": {
"TrainerController._reset_env": {
"total": 9.552144519000024,
"count": 1,
"self": 9.552144519000024
},
"TrainerController.advance": {
"total": 438.05344694399605,
"count": 18201,
"self": 0.2651557720003552,
"children": {
"env_step": {
"total": 437.7882911719957,
"count": 18201,
"self": 298.888728039001,
"children": {
"SubprocessEnvManager._take_step": {
"total": 138.63764871599284,
"count": 18201,
"self": 1.5922418609947613,
"children": {
"TorchPolicy.evaluate": {
"total": 137.04540685499808,
"count": 18201,
"self": 29.504855445988824,
"children": {
"TorchPolicy.sample_actions": {
"total": 107.54055140900925,
"count": 18201,
"self": 107.54055140900925
}
}
}
}
},
"workers": {
"total": 0.26191441700183304,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 446.71421163300744,
"count": 18201,
"is_parallel": true,
"self": 218.65813898400467,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008661363999976857,
"count": 1,
"is_parallel": true,
"self": 0.004328504000113753,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0043328599998631034,
"count": 10,
"is_parallel": true,
"self": 0.0043328599998631034
}
}
},
"UnityEnvironment.step": {
"total": 0.045197137000002385,
"count": 1,
"is_parallel": true,
"self": 0.0003508359999955246,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00034329299995761176,
"count": 1,
"is_parallel": true,
"self": 0.00034329299995761176
},
"communicator.exchange": {
"total": 0.04331917100000737,
"count": 1,
"is_parallel": true,
"self": 0.04331917100000737
},
"steps_from_proto": {
"total": 0.0011838370000418763,
"count": 1,
"is_parallel": true,
"self": 0.0003216740000766549,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008621629999652214,
"count": 10,
"is_parallel": true,
"self": 0.0008621629999652214
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 228.05607264900277,
"count": 18200,
"is_parallel": true,
"self": 9.394964776007953,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.012264174998165,
"count": 18200,
"is_parallel": true,
"self": 5.012264174998165
},
"communicator.exchange": {
"total": 183.37433795599992,
"count": 18200,
"is_parallel": true,
"self": 183.37433795599992
},
"steps_from_proto": {
"total": 30.274505741996734,
"count": 18200,
"is_parallel": true,
"self": 6.4395041069790295,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.835001635017704,
"count": 182000,
"is_parallel": true,
"self": 23.835001635017704
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013461499997902138,
"count": 1,
"self": 0.00013461499997902138,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 434.8651515259835,
"count": 396972,
"is_parallel": true,
"self": 9.601483558958137,
"children": {
"process_trajectory": {
"total": 248.18959724702597,
"count": 396972,
"is_parallel": true,
"self": 247.48483075102604,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7047664959999338,
"count": 4,
"is_parallel": true,
"self": 0.7047664959999338
}
}
},
"_update_policy": {
"total": 177.07407071999938,
"count": 90,
"is_parallel": true,
"self": 60.913005051999505,
"children": {
"TorchPPOOptimizer.update": {
"total": 116.16106566799988,
"count": 4587,
"is_parallel": true,
"self": 116.16106566799988
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12589715900003284,
"count": 1,
"self": 0.0008490940000456249,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12504806499998722,
"count": 1,
"self": 0.12504806499998722
}
}
}
}
}
}
}