Huggingfly's picture
First Push
e5f59cd
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.078853726387024,
"min": 1.070643424987793,
"max": 2.865523099899292,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10312.7626953125,
"min": 10312.7626953125,
"max": 29345.822265625,
"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": 12.81618595123291,
"min": 0.2958076000213623,
"max": 12.81618595123291,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2499.15625,
"min": 57.38667678833008,
"max": 2596.1318359375,
"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": 0.06762157291600221,
"min": 0.0625208076770957,
"max": 0.0738958894840371,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27048629166400884,
"min": 0.2593368875243993,
"max": 0.36695702997602375,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.211254061144941,
"min": 0.11845652494972171,
"max": 0.2831909546080757,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.845016244579764,
"min": 0.47382609979888685,
"max": 1.4159547730403785,
"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": 25.363636363636363,
"min": 3.5,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1116.0,
"min": 154.0,
"max": 1392.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.363636363636363,
"min": 3.5,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1116.0,
"min": 154.0,
"max": 1392.0,
"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": "1688844695",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1688845197"
},
"total": 501.40366257299996,
"count": 1,
"self": 0.4887489879999407,
"children": {
"run_training.setup": {
"total": 0.07244424200001731,
"count": 1,
"self": 0.07244424200001731
},
"TrainerController.start_learning": {
"total": 500.842469343,
"count": 1,
"self": 0.625857143998303,
"children": {
"TrainerController._reset_env": {
"total": 4.959841544999961,
"count": 1,
"self": 4.959841544999961
},
"TrainerController.advance": {
"total": 495.1125642650016,
"count": 18201,
"self": 0.29721969300624096,
"children": {
"env_step": {
"total": 494.81534457199535,
"count": 18201,
"self": 360.1802709729833,
"children": {
"SubprocessEnvManager._take_step": {
"total": 134.34916879900857,
"count": 18201,
"self": 1.8763047490074882,
"children": {
"TorchPolicy.evaluate": {
"total": 132.47286405000108,
"count": 18201,
"self": 132.47286405000108
}
}
},
"workers": {
"total": 0.28590480000349316,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 499.1860257009932,
"count": 18201,
"is_parallel": true,
"self": 231.84801253699044,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007391610000013316,
"count": 1,
"is_parallel": true,
"self": 0.0049006010001448885,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002491008999868427,
"count": 10,
"is_parallel": true,
"self": 0.002491008999868427
}
}
},
"UnityEnvironment.step": {
"total": 0.048428190999970866,
"count": 1,
"is_parallel": true,
"self": 0.00045868099994095246,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004586200000176177,
"count": 1,
"is_parallel": true,
"self": 0.0004586200000176177
},
"communicator.exchange": {
"total": 0.04605387999998811,
"count": 1,
"is_parallel": true,
"self": 0.04605387999998811
},
"steps_from_proto": {
"total": 0.0014570100000241837,
"count": 1,
"is_parallel": true,
"self": 0.00027636200002234546,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011806480000018382,
"count": 10,
"is_parallel": true,
"self": 0.0011806480000018382
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 267.33801316400275,
"count": 18200,
"is_parallel": true,
"self": 11.133628286011287,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.543002228992975,
"count": 18200,
"is_parallel": true,
"self": 5.543002228992975
},
"communicator.exchange": {
"total": 213.24499983699178,
"count": 18200,
"is_parallel": true,
"self": 213.24499983699178
},
"steps_from_proto": {
"total": 37.4163828120067,
"count": 18200,
"is_parallel": true,
"self": 6.789373310020437,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.627009501986265,
"count": 182000,
"is_parallel": true,
"self": 30.627009501986265
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014959900011035643,
"count": 1,
"self": 0.00014959900011035643,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 491.2578100510111,
"count": 481176,
"is_parallel": true,
"self": 10.913105881008562,
"children": {
"process_trajectory": {
"total": 270.5475156070027,
"count": 481176,
"is_parallel": true,
"self": 268.9155977250029,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6319178819998115,
"count": 4,
"is_parallel": true,
"self": 1.6319178819998115
}
}
},
"_update_policy": {
"total": 209.79718856299985,
"count": 90,
"is_parallel": true,
"self": 81.46900890099829,
"children": {
"TorchPPOOptimizer.update": {
"total": 128.32817966200156,
"count": 4587,
"is_parallel": true,
"self": 128.32817966200156
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14405679000003602,
"count": 1,
"self": 0.0009391490000325575,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14311764100000346,
"count": 1,
"self": 0.14311764100000346
}
}
}
}
}
}
}