SuperDan's picture
First Push
b7934e7
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9145268797874451,
"min": 0.9145268797874451,
"max": 2.863192081451416,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8752.0224609375,
"min": 8752.0224609375,
"max": 29542.416015625,
"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": 12.902938842773438,
"min": 0.3684549331665039,
"max": 12.902938842773438,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2516.072998046875,
"min": 71.48025512695312,
"max": 2586.4111328125,
"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": 0.06808955707503414,
"min": 0.062049163048447785,
"max": 0.07451926020782111,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27235822830013656,
"min": 0.266116453187886,
"max": 0.3712524771901514,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19405895544617785,
"min": 0.13207029811261844,
"max": 0.29259772680553736,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7762358217847114,
"min": 0.5282811924504738,
"max": 1.4629886340276868,
"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": 25.90909090909091,
"min": 3.772727272727273,
"max": 25.90909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1140.0,
"min": 166.0,
"max": 1389.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.90909090909091,
"min": 3.772727272727273,
"max": 25.90909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1140.0,
"min": 166.0,
"max": 1389.0,
"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": "1700653099",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1700653592"
},
"total": 492.41959432999965,
"count": 1,
"self": 0.42428526999992755,
"children": {
"run_training.setup": {
"total": 0.04535811699997794,
"count": 1,
"self": 0.04535811699997794
},
"TrainerController.start_learning": {
"total": 491.94995094299975,
"count": 1,
"self": 0.5862305430318884,
"children": {
"TrainerController._reset_env": {
"total": 10.078609041000163,
"count": 1,
"self": 10.078609041000163
},
"TrainerController.advance": {
"total": 481.1930156579674,
"count": 18201,
"self": 0.27968190795763803,
"children": {
"env_step": {
"total": 480.91333375000977,
"count": 18201,
"self": 327.9733230630395,
"children": {
"SubprocessEnvManager._take_step": {
"total": 152.6499106149904,
"count": 18201,
"self": 1.4926019800091126,
"children": {
"TorchPolicy.evaluate": {
"total": 151.1573086349813,
"count": 18201,
"self": 151.1573086349813
}
}
},
"workers": {
"total": 0.2901000719798503,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 490.53107591899925,
"count": 18201,
"is_parallel": true,
"self": 241.15713930101492,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00499680700022509,
"count": 1,
"is_parallel": true,
"self": 0.003613209000832285,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001383597999392805,
"count": 10,
"is_parallel": true,
"self": 0.001383597999392805
}
}
},
"UnityEnvironment.step": {
"total": 0.03761007699995389,
"count": 1,
"is_parallel": true,
"self": 0.0005423649995464075,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004961540003023401,
"count": 1,
"is_parallel": true,
"self": 0.0004961540003023401
},
"communicator.exchange": {
"total": 0.03441019000001688,
"count": 1,
"is_parallel": true,
"self": 0.03441019000001688
},
"steps_from_proto": {
"total": 0.0021613680000882596,
"count": 1,
"is_parallel": true,
"self": 0.000448281000899442,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017130869991888176,
"count": 10,
"is_parallel": true,
"self": 0.0017130869991888176
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 249.37393661798433,
"count": 18200,
"is_parallel": true,
"self": 11.014312946966584,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.723541617020146,
"count": 18200,
"is_parallel": true,
"self": 5.723541617020146
},
"communicator.exchange": {
"total": 196.54542563698988,
"count": 18200,
"is_parallel": true,
"self": 196.54542563698988
},
"steps_from_proto": {
"total": 36.09065641700772,
"count": 18200,
"is_parallel": true,
"self": 6.8378210139671864,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.252835403040535,
"count": 182000,
"is_parallel": true,
"self": 29.252835403040535
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016355900015696534,
"count": 1,
"self": 0.00016355900015696534,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 477.0553882198287,
"count": 507627,
"is_parallel": true,
"self": 10.803910247936528,
"children": {
"process_trajectory": {
"total": 271.14753196388983,
"count": 507627,
"is_parallel": true,
"self": 270.35583532089004,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7916966429997956,
"count": 4,
"is_parallel": true,
"self": 0.7916966429997956
}
}
},
"_update_policy": {
"total": 195.10394600800237,
"count": 90,
"is_parallel": true,
"self": 63.051480985000126,
"children": {
"TorchPPOOptimizer.update": {
"total": 132.05246502300224,
"count": 4584,
"is_parallel": true,
"self": 132.05246502300224
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09193214200013244,
"count": 1,
"self": 0.0008123289999275585,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09111981300020489,
"count": 1,
"self": 0.09111981300020489
}
}
}
}
}
}
}