tommytran's picture
First Push
782602d
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8655300736427307,
"min": 0.8655300736427307,
"max": 2.8697171211242676,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8264.0810546875,
"min": 8264.0810546875,
"max": 29388.7734375,
"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": 13.10120964050293,
"min": 0.5027732253074646,
"max": 13.10120964050293,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2554.73583984375,
"min": 97.53800964355469,
"max": 2669.233642578125,
"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": 0.06584944961222766,
"min": 0.061526663286677635,
"max": 0.07510094758172807,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26339779844891065,
"min": 0.24610665314671054,
"max": 0.37550473790864036,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1940659137040961,
"min": 0.12883010741629108,
"max": 0.2835859814695284,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7762636548163844,
"min": 0.5153204296651643,
"max": 1.417929907347642,
"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": 25.795454545454547,
"min": 4.0,
"max": 26.09090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1135.0,
"min": 176.0,
"max": 1435.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.795454545454547,
"min": 4.0,
"max": 26.09090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1135.0,
"min": 176.0,
"max": 1435.0,
"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": "1681149617",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1681150061"
},
"total": 443.68520902599994,
"count": 1,
"self": 0.42836407599997983,
"children": {
"run_training.setup": {
"total": 0.12057420299993282,
"count": 1,
"self": 0.12057420299993282
},
"TrainerController.start_learning": {
"total": 443.136270747,
"count": 1,
"self": 0.5129442019975841,
"children": {
"TrainerController._reset_env": {
"total": 3.88677408500007,
"count": 1,
"self": 3.88677408500007
},
"TrainerController.advance": {
"total": 438.6079728680023,
"count": 18201,
"self": 0.263185350009735,
"children": {
"env_step": {
"total": 438.3447875179926,
"count": 18201,
"self": 322.0212875929841,
"children": {
"SubprocessEnvManager._take_step": {
"total": 116.06867165200049,
"count": 18201,
"self": 1.5783605060021273,
"children": {
"TorchPolicy.evaluate": {
"total": 114.49031114599836,
"count": 18201,
"self": 114.49031114599836
}
}
},
"workers": {
"total": 0.2548282730080018,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 441.6773306950039,
"count": 18201,
"is_parallel": true,
"self": 206.31539211399206,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004843316000005871,
"count": 1,
"is_parallel": true,
"self": 0.0034040589998767246,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001439257000129146,
"count": 10,
"is_parallel": true,
"self": 0.001439257000129146
}
}
},
"UnityEnvironment.step": {
"total": 0.035071907000087776,
"count": 1,
"is_parallel": true,
"self": 0.0005945540002585403,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003261699999939083,
"count": 1,
"is_parallel": true,
"self": 0.0003261699999939083
},
"communicator.exchange": {
"total": 0.03224887699991541,
"count": 1,
"is_parallel": true,
"self": 0.03224887699991541
},
"steps_from_proto": {
"total": 0.0019023059999199177,
"count": 1,
"is_parallel": true,
"self": 0.00039415300011569343,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015081529998042242,
"count": 10,
"is_parallel": true,
"self": 0.0015081529998042242
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 235.36193858101183,
"count": 18200,
"is_parallel": true,
"self": 9.615128422043426,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.312842888998375,
"count": 18200,
"is_parallel": true,
"self": 5.312842888998375
},
"communicator.exchange": {
"total": 190.00548919198172,
"count": 18200,
"is_parallel": true,
"self": 190.00548919198172
},
"steps_from_proto": {
"total": 30.428478077988302,
"count": 18200,
"is_parallel": true,
"self": 5.808431461996406,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.620046615991896,
"count": 182000,
"is_parallel": true,
"self": 24.620046615991896
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013403599996308913,
"count": 1,
"self": 0.00013403599996308913,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 435.2588429560574,
"count": 391973,
"is_parallel": true,
"self": 9.717488716063485,
"children": {
"process_trajectory": {
"total": 239.09389426799453,
"count": 391973,
"is_parallel": true,
"self": 238.3486739559945,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7452203120000149,
"count": 4,
"is_parallel": true,
"self": 0.7452203120000149
}
}
},
"_update_policy": {
"total": 186.44745997199936,
"count": 90,
"is_parallel": true,
"self": 70.27931828999863,
"children": {
"TorchPPOOptimizer.update": {
"total": 116.16814168200074,
"count": 4587,
"is_parallel": true,
"self": 116.16814168200074
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1284455560000879,
"count": 1,
"self": 0.0008688279999660153,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12757672800012188,
"count": 1,
"self": 0.12757672800012188
}
}
}
}
}
}
}