ppo / run_logs /timers.json
Convolution's picture
First attempt
a078223
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.929318368434906,
"min": 0.929318368434906,
"max": 2.8686089515686035,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8873.1318359375,
"min": 8873.1318359375,
"max": 29377.423828125,
"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": 13.011645317077637,
"min": 0.42045652866363525,
"max": 13.011645317077637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2537.270751953125,
"min": 81.56856536865234,
"max": 2640.6279296875,
"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": 0.07383147778776165,
"min": 0.06106905659487216,
"max": 0.07388739740046872,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2953259111510466,
"min": 0.2502201266573084,
"max": 0.3691032917941258,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19132964678254782,
"min": 0.11601415771977319,
"max": 0.3185094995241539,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7653185871301913,
"min": 0.46405663087909277,
"max": 1.390244236763786,
"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": 26.0,
"min": 3.1818181818181817,
"max": 26.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1144.0,
"min": 140.0,
"max": 1410.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.0,
"min": 3.1818181818181817,
"max": 26.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1144.0,
"min": 140.0,
"max": 1410.0,
"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": "1673812646",
"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": "1673813057"
},
"total": 411.0419564550001,
"count": 1,
"self": 0.38755401900004927,
"children": {
"run_training.setup": {
"total": 0.1054642579999836,
"count": 1,
"self": 0.1054642579999836
},
"TrainerController.start_learning": {
"total": 410.54893817800007,
"count": 1,
"self": 0.48771029901138263,
"children": {
"TrainerController._reset_env": {
"total": 9.193761530000074,
"count": 1,
"self": 9.193761530000074
},
"TrainerController.advance": {
"total": 400.7555781629886,
"count": 18202,
"self": 0.2556825989756817,
"children": {
"env_step": {
"total": 400.49989556401295,
"count": 18202,
"self": 260.38438982299897,
"children": {
"SubprocessEnvManager._take_step": {
"total": 139.86065947901363,
"count": 18202,
"self": 1.3097103400114065,
"children": {
"TorchPolicy.evaluate": {
"total": 138.55094913900223,
"count": 18202,
"self": 30.837523657995803,
"children": {
"TorchPolicy.sample_actions": {
"total": 107.71342548100642,
"count": 18202,
"self": 107.71342548100642
}
}
}
}
},
"workers": {
"total": 0.254846262000342,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 409.45110147100945,
"count": 18202,
"is_parallel": true,
"self": 200.22014720200718,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006069663000062064,
"count": 1,
"is_parallel": true,
"self": 0.0036525890000120853,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002417074000049979,
"count": 10,
"is_parallel": true,
"self": 0.002417074000049979
}
}
},
"UnityEnvironment.step": {
"total": 0.03363810799999101,
"count": 1,
"is_parallel": true,
"self": 0.0005087599997750658,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003750130000526042,
"count": 1,
"is_parallel": true,
"self": 0.0003750130000526042
},
"communicator.exchange": {
"total": 0.03093270500005474,
"count": 1,
"is_parallel": true,
"self": 0.03093270500005474
},
"steps_from_proto": {
"total": 0.0018216300001085983,
"count": 1,
"is_parallel": true,
"self": 0.0004353110002739413,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001386318999834657,
"count": 10,
"is_parallel": true,
"self": 0.001386318999834657
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 209.23095426900227,
"count": 18201,
"is_parallel": true,
"self": 8.133703401017897,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.8073246809959755,
"count": 18201,
"is_parallel": true,
"self": 4.8073246809959755
},
"communicator.exchange": {
"total": 167.39989165099655,
"count": 18201,
"is_parallel": true,
"self": 167.39989165099655
},
"steps_from_proto": {
"total": 28.890034535991845,
"count": 18201,
"is_parallel": true,
"self": 6.0998048759629455,
"children": {
"_process_rank_one_or_two_observation": {
"total": 22.7902296600289,
"count": 182010,
"is_parallel": true,
"self": 22.7902296600289
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.372500006866176e-05,
"count": 1,
"self": 4.372500006866176e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 398.0025425560001,
"count": 320909,
"is_parallel": true,
"self": 8.299800122009742,
"children": {
"process_trajectory": {
"total": 228.33949540099115,
"count": 320909,
"is_parallel": true,
"self": 227.66015625099112,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6793391500000325,
"count": 4,
"is_parallel": true,
"self": 0.6793391500000325
}
}
},
"_update_policy": {
"total": 161.3632470329992,
"count": 90,
"is_parallel": true,
"self": 40.803390248005144,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.55985678499405,
"count": 4587,
"is_parallel": true,
"self": 120.55985678499405
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11184446099991874,
"count": 1,
"self": 0.0008586199999172095,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11098584100000153,
"count": 1,
"self": 0.11098584100000153
}
}
}
}
}
}
}