Clawoo's picture
First push
1a037b4
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7233498692512512,
"min": 0.7233498692512512,
"max": 2.870417833328247,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6898.587890625,
"min": 6898.587890625,
"max": 29427.5234375,
"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": 12.932974815368652,
"min": 0.29860278964042664,
"max": 12.932974815368652,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2521.93017578125,
"min": 57.92893981933594,
"max": 2599.512451171875,
"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": 0.07092624623481812,
"min": 0.06259994988612758,
"max": 0.07724791831501267,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2837049849392725,
"min": 0.2563379147575367,
"max": 0.3862395915750633,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20085805092079967,
"min": 0.12431970683118218,
"max": 0.26616955329390135,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8034322036831987,
"min": 0.4972788273247287,
"max": 1.3051682044478023,
"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": 25.227272727272727,
"min": 3.522727272727273,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1110.0,
"min": 155.0,
"max": 1415.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.227272727272727,
"min": 3.522727272727273,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1110.0,
"min": 155.0,
"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": "1673367331",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "1673367758"
},
"total": 427.53601023600004,
"count": 1,
"self": 0.3863358770000218,
"children": {
"run_training.setup": {
"total": 0.10667231899998342,
"count": 1,
"self": 0.10667231899998342
},
"TrainerController.start_learning": {
"total": 427.04300204000003,
"count": 1,
"self": 0.4856721450011037,
"children": {
"TrainerController._reset_env": {
"total": 7.134395314000017,
"count": 1,
"self": 7.134395314000017
},
"TrainerController.advance": {
"total": 419.2950154949989,
"count": 18200,
"self": 0.25753612399478243,
"children": {
"env_step": {
"total": 419.0374793710041,
"count": 18200,
"self": 272.1566227169942,
"children": {
"SubprocessEnvManager._take_step": {
"total": 146.62879099700274,
"count": 18200,
"self": 1.3570870480136819,
"children": {
"TorchPolicy.evaluate": {
"total": 145.27170394898906,
"count": 18200,
"self": 31.824543443991956,
"children": {
"TorchPolicy.sample_actions": {
"total": 113.4471605049971,
"count": 18200,
"self": 113.4471605049971
}
}
}
}
},
"workers": {
"total": 0.2520656570071651,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 425.87194113299984,
"count": 18200,
"is_parallel": true,
"self": 206.98308628299162,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007067553000013049,
"count": 1,
"is_parallel": true,
"self": 0.004482623999990665,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0025849290000223846,
"count": 10,
"is_parallel": true,
"self": 0.0025849290000223846
}
}
},
"UnityEnvironment.step": {
"total": 0.04169229300009647,
"count": 1,
"is_parallel": true,
"self": 0.0005113590002565616,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003164720000086163,
"count": 1,
"is_parallel": true,
"self": 0.0003164720000086163
},
"communicator.exchange": {
"total": 0.039121364999914476,
"count": 1,
"is_parallel": true,
"self": 0.039121364999914476
},
"steps_from_proto": {
"total": 0.0017430969999168155,
"count": 1,
"is_parallel": true,
"self": 0.00039820400013468316,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013448929997821324,
"count": 10,
"is_parallel": true,
"self": 0.0013448929997821324
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 218.88885485000822,
"count": 18199,
"is_parallel": true,
"self": 8.41147109901658,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.8683423689940355,
"count": 18199,
"is_parallel": true,
"self": 4.8683423689940355
},
"communicator.exchange": {
"total": 175.47739907899677,
"count": 18199,
"is_parallel": true,
"self": 175.47739907899677
},
"steps_from_proto": {
"total": 30.13164230300083,
"count": 18199,
"is_parallel": true,
"self": 6.411001564019102,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.72064073898173,
"count": 181990,
"is_parallel": true,
"self": 23.72064073898173
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.195200006051891e-05,
"count": 1,
"self": 4.195200006051891e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 416.4152163240241,
"count": 331415,
"is_parallel": true,
"self": 9.090368935083461,
"children": {
"process_trajectory": {
"total": 237.73618055594045,
"count": 331415,
"is_parallel": true,
"self": 237.0275696479406,
"children": {
"RLTrainer._checkpoint": {
"total": 0.708610907999855,
"count": 4,
"is_parallel": true,
"self": 0.708610907999855
}
}
},
"_update_policy": {
"total": 169.58866683300016,
"count": 90,
"is_parallel": true,
"self": 44.23270657600267,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.35596025699749,
"count": 4587,
"is_parallel": true,
"self": 125.35596025699749
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12787713399995937,
"count": 1,
"self": 0.0008486389999688981,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12702849499999047,
"count": 1,
"self": 0.12702849499999047
}
}
}
}
}
}
}