robinsk8a's picture
First Push
848d336
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9041341543197632,
"min": 0.9041341543197632,
"max": 2.8625001907348633,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8622.7275390625,
"min": 8622.7275390625,
"max": 29314.86328125,
"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": 12.27362060546875,
"min": 0.3669624626636505,
"max": 12.27362060546875,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2393.35595703125,
"min": 71.19071960449219,
"max": 2485.3974609375,
"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": 0.06806632124076428,
"min": 0.0616784173832332,
"max": 0.07718946284833639,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27226528496305713,
"min": 0.2467136695329328,
"max": 0.3854859917260268,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19352510169732803,
"min": 0.12390590772288394,
"max": 0.28875528736149564,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7741004067893121,
"min": 0.49562363089153577,
"max": 1.3212228727106954,
"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": 24.15909090909091,
"min": 3.227272727272727,
"max": 24.15909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1063.0,
"min": 142.0,
"max": 1322.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.15909090909091,
"min": 3.227272727272727,
"max": 24.15909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1063.0,
"min": 142.0,
"max": 1322.0,
"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": "1675978566",
"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": "1675979077"
},
"total": 511.311997326,
"count": 1,
"self": 0.44070924200002537,
"children": {
"run_training.setup": {
"total": 0.1159165669999993,
"count": 1,
"self": 0.1159165669999993
},
"TrainerController.start_learning": {
"total": 510.75537151699996,
"count": 1,
"self": 0.5995452229920488,
"children": {
"TrainerController._reset_env": {
"total": 8.531453079000016,
"count": 1,
"self": 8.531453079000016
},
"TrainerController.advance": {
"total": 501.4856809470079,
"count": 18203,
"self": 0.31803190500357914,
"children": {
"env_step": {
"total": 501.1676490420043,
"count": 18203,
"self": 345.6887663720192,
"children": {
"SubprocessEnvManager._take_step": {
"total": 155.1671988209893,
"count": 18203,
"self": 1.6251685539972982,
"children": {
"TorchPolicy.evaluate": {
"total": 153.54203026699201,
"count": 18203,
"self": 34.33189480699576,
"children": {
"TorchPolicy.sample_actions": {
"total": 119.21013545999625,
"count": 18203,
"self": 119.21013545999625
}
}
}
}
},
"workers": {
"total": 0.3116838489958127,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 508.94127161000955,
"count": 18203,
"is_parallel": true,
"self": 248.38452682300033,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005423463999989053,
"count": 1,
"is_parallel": true,
"self": 0.003098353999973824,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002325110000015229,
"count": 10,
"is_parallel": true,
"self": 0.002325110000015229
}
}
},
"UnityEnvironment.step": {
"total": 0.03690393900001254,
"count": 1,
"is_parallel": true,
"self": 0.0006201089999535725,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042916099999956714,
"count": 1,
"is_parallel": true,
"self": 0.00042916099999956714
},
"communicator.exchange": {
"total": 0.03361649000004263,
"count": 1,
"is_parallel": true,
"self": 0.03361649000004263
},
"steps_from_proto": {
"total": 0.002238179000016771,
"count": 1,
"is_parallel": true,
"self": 0.00046338600003537067,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017747929999814005,
"count": 10,
"is_parallel": true,
"self": 0.0017747929999814005
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 260.5567447870092,
"count": 18202,
"is_parallel": true,
"self": 10.354191911012322,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.879791044996864,
"count": 18202,
"is_parallel": true,
"self": 5.879791044996864
},
"communicator.exchange": {
"total": 208.45999079599835,
"count": 18202,
"is_parallel": true,
"self": 208.45999079599835
},
"steps_from_proto": {
"total": 35.862771035001686,
"count": 18202,
"is_parallel": true,
"self": 7.940003326022008,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.922767708979677,
"count": 182020,
"is_parallel": true,
"self": 27.922767708979677
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013896500001919776,
"count": 1,
"self": 0.00013896500001919776,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 497.49139031401796,
"count": 439138,
"is_parallel": true,
"self": 11.652231834994495,
"children": {
"process_trajectory": {
"total": 283.5787045270234,
"count": 439138,
"is_parallel": true,
"self": 282.57351160502327,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0051929220001057,
"count": 4,
"is_parallel": true,
"self": 1.0051929220001057
}
}
},
"_update_policy": {
"total": 202.2604539520001,
"count": 90,
"is_parallel": true,
"self": 74.66155076700306,
"children": {
"TorchPPOOptimizer.update": {
"total": 127.59890318499703,
"count": 4587,
"is_parallel": true,
"self": 127.59890318499703
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1385533029999806,
"count": 1,
"self": 0.0009057629999915662,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13764753999998902,
"count": 1,
"self": 0.13764753999998902
}
}
}
}
}
}
}