raulgadea's picture
First Push
436728b verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9792397618293762,
"min": 0.9792397618293762,
"max": 2.879291296005249,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9360.552734375,
"min": 9360.552734375,
"max": 29486.822265625,
"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": 12.808253288269043,
"min": 0.21608851850032806,
"max": 12.808253288269043,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2497.609375,
"min": 41.921173095703125,
"max": 2589.96630859375,
"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": 0.06409594664764169,
"min": 0.061643529085849164,
"max": 0.0755824831150034,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25638378659056676,
"min": 0.24657411634339665,
"max": 0.377912415575017,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21880664055546126,
"min": 0.09460735507994232,
"max": 0.28747571142865164,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.875226562221845,
"min": 0.3784294203197693,
"max": 1.366181742326886,
"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": 25.545454545454547,
"min": 2.659090909090909,
"max": 25.69090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1124.0,
"min": 117.0,
"max": 1413.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.545454545454547,
"min": 2.659090909090909,
"max": 25.69090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1124.0,
"min": 117.0,
"max": 1413.0,
"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": "1714924491",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714924988"
},
"total": 496.6670653730001,
"count": 1,
"self": 0.43676939100009804,
"children": {
"run_training.setup": {
"total": 0.05805205299998306,
"count": 1,
"self": 0.05805205299998306
},
"TrainerController.start_learning": {
"total": 496.17224392900005,
"count": 1,
"self": 0.6909301170028357,
"children": {
"TrainerController._reset_env": {
"total": 2.7102979549999873,
"count": 1,
"self": 2.7102979549999873
},
"TrainerController.advance": {
"total": 492.66190714399715,
"count": 18200,
"self": 0.31965830798924344,
"children": {
"env_step": {
"total": 492.3422488360079,
"count": 18200,
"self": 321.9897404449788,
"children": {
"SubprocessEnvManager._take_step": {
"total": 170.00371889000894,
"count": 18200,
"self": 1.661127039018993,
"children": {
"TorchPolicy.evaluate": {
"total": 168.34259185098995,
"count": 18200,
"self": 168.34259185098995
}
}
},
"workers": {
"total": 0.34878950102017825,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 494.70392278899624,
"count": 18200,
"is_parallel": true,
"self": 243.007551641987,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0059052100000371865,
"count": 1,
"is_parallel": true,
"self": 0.004201753000074859,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017034569999623272,
"count": 10,
"is_parallel": true,
"self": 0.0017034569999623272
}
}
},
"UnityEnvironment.step": {
"total": 0.0437766620000275,
"count": 1,
"is_parallel": true,
"self": 0.0007332200000291778,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004471839999951044,
"count": 1,
"is_parallel": true,
"self": 0.0004471839999951044
},
"communicator.exchange": {
"total": 0.04027602799999386,
"count": 1,
"is_parallel": true,
"self": 0.04027602799999386
},
"steps_from_proto": {
"total": 0.00232023000000936,
"count": 1,
"is_parallel": true,
"self": 0.00046159099997566955,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018586390000336905,
"count": 10,
"is_parallel": true,
"self": 0.0018586390000336905
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 251.69637114700924,
"count": 18199,
"is_parallel": true,
"self": 11.27636117200575,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.167422648991874,
"count": 18199,
"is_parallel": true,
"self": 6.167422648991874
},
"communicator.exchange": {
"total": 195.9619310150083,
"count": 18199,
"is_parallel": true,
"self": 195.9619310150083
},
"steps_from_proto": {
"total": 38.29065631100332,
"count": 18199,
"is_parallel": true,
"self": 7.392863098004341,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.897793212998977,
"count": 181990,
"is_parallel": true,
"self": 30.897793212998977
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012598500006788527,
"count": 1,
"self": 0.00012598500006788527,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 486.30958893096704,
"count": 741054,
"is_parallel": true,
"self": 16.225135885986333,
"children": {
"process_trajectory": {
"total": 270.73359333298106,
"count": 741054,
"is_parallel": true,
"self": 270.1294314819811,
"children": {
"RLTrainer._checkpoint": {
"total": 0.604161850999958,
"count": 4,
"is_parallel": true,
"self": 0.604161850999958
}
}
},
"_update_policy": {
"total": 199.35085971199965,
"count": 90,
"is_parallel": true,
"self": 57.32964697499858,
"children": {
"TorchPPOOptimizer.update": {
"total": 142.02121273700106,
"count": 4587,
"is_parallel": true,
"self": 142.02121273700106
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10898272800000086,
"count": 1,
"self": 0.003124786999933349,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10585794100006751,
"count": 1,
"self": 0.10585794100006751
}
}
}
}
}
}
}