johnhudzinatr's picture
First Push
c74ad27
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8302966952323914,
"min": 0.8302966952323914,
"max": 2.8749756813049316,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7927.6728515625,
"min": 7927.6728515625,
"max": 29442.625,
"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": 12.796381950378418,
"min": 0.2597545385360718,
"max": 12.796381950378418,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2495.29443359375,
"min": 50.39237976074219,
"max": 2587.78125,
"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": 0.07211652786598022,
"min": 0.06248123422866212,
"max": 0.07546102818525077,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28846611146392087,
"min": 0.2502357267441374,
"max": 0.37730514092625383,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.182281004447563,
"min": 0.10922727790688548,
"max": 0.3053367517012007,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.729124017790252,
"min": 0.4369091116275419,
"max": 1.3334877055649663,
"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": 25.181818181818183,
"min": 3.1818181818181817,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1108.0,
"min": 140.0,
"max": 1415.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.181818181818183,
"min": 3.1818181818181817,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1108.0,
"min": 140.0,
"max": 1415.0,
"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": "1674333275",
"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": "1674333717"
},
"total": 442.34020558299994,
"count": 1,
"self": 0.43913312099982704,
"children": {
"run_training.setup": {
"total": 0.11178632300004665,
"count": 1,
"self": 0.11178632300004665
},
"TrainerController.start_learning": {
"total": 441.78928613900007,
"count": 1,
"self": 0.6022302340037413,
"children": {
"TrainerController._reset_env": {
"total": 10.994426960999931,
"count": 1,
"self": 10.994426960999931
},
"TrainerController.advance": {
"total": 430.06917818299644,
"count": 18201,
"self": 0.2993407899916747,
"children": {
"env_step": {
"total": 429.76983739300476,
"count": 18201,
"self": 282.03076079102686,
"children": {
"SubprocessEnvManager._take_step": {
"total": 147.457818328985,
"count": 18201,
"self": 1.4406199709851535,
"children": {
"TorchPolicy.evaluate": {
"total": 146.01719835799986,
"count": 18201,
"self": 32.72967727401817,
"children": {
"TorchPolicy.sample_actions": {
"total": 113.28752108398169,
"count": 18201,
"self": 113.28752108398169
}
}
}
}
},
"workers": {
"total": 0.2812582729928863,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 440.45187846299314,
"count": 18201,
"is_parallel": true,
"self": 208.79389494399186,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005374283000037394,
"count": 1,
"is_parallel": true,
"self": 0.00313734700000623,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022369360000311644,
"count": 10,
"is_parallel": true,
"self": 0.0022369360000311644
}
}
},
"UnityEnvironment.step": {
"total": 0.04889236799999708,
"count": 1,
"is_parallel": true,
"self": 0.0004909709999765255,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002964960000326755,
"count": 1,
"is_parallel": true,
"self": 0.0002964960000326755
},
"communicator.exchange": {
"total": 0.04626139599997714,
"count": 1,
"is_parallel": true,
"self": 0.04626139599997714
},
"steps_from_proto": {
"total": 0.0018435050000107367,
"count": 1,
"is_parallel": true,
"self": 0.0004434130000845471,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014000919999261896,
"count": 10,
"is_parallel": true,
"self": 0.0014000919999261896
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 231.65798351900128,
"count": 18200,
"is_parallel": true,
"self": 8.64663565699118,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.043741476013224,
"count": 18200,
"is_parallel": true,
"self": 5.043741476013224
},
"communicator.exchange": {
"total": 185.1700355559915,
"count": 18200,
"is_parallel": true,
"self": 185.1700355559915
},
"steps_from_proto": {
"total": 32.797570830005384,
"count": 18200,
"is_parallel": true,
"self": 6.815447177032183,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.9821236529732,
"count": 182000,
"is_parallel": true,
"self": 25.9821236529732
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.1216999963799026e-05,
"count": 1,
"self": 5.1216999963799026e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 427.14915121402703,
"count": 352632,
"is_parallel": true,
"self": 9.235061349940338,
"children": {
"process_trajectory": {
"total": 245.6296754290861,
"count": 352632,
"is_parallel": true,
"self": 244.91498267508632,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7146927539997705,
"count": 4,
"is_parallel": true,
"self": 0.7146927539997705
}
}
},
"_update_policy": {
"total": 172.2844144350006,
"count": 90,
"is_parallel": true,
"self": 41.59285721899653,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.69155721600407,
"count": 4587,
"is_parallel": true,
"self": 130.69155721600407
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12339954399999442,
"count": 1,
"self": 0.0009056839999175281,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12249386000007689,
"count": 1,
"self": 0.12249386000007689
}
}
}
}
}
}
}