sekinat's picture
First Push
933e8cd
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9973807334899902,
"min": 0.9973807334899902,
"max": 2.8636648654937744,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9522.9912109375,
"min": 9522.9912109375,
"max": 29358.291015625,
"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": 12.752532005310059,
"min": 0.4444074034690857,
"max": 12.752532005310059,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2486.74365234375,
"min": 86.21503448486328,
"max": 2578.818115234375,
"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": 0.06495306335808196,
"min": 0.06366134664858691,
"max": 0.07413071839266694,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25981225343232783,
"min": 0.25464538659434766,
"max": 0.3706535919633347,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20199109964510975,
"min": 0.122475234758538,
"max": 0.2892059404768196,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.807964398580439,
"min": 0.489900939034152,
"max": 1.4282018802329606,
"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": 25.295454545454547,
"min": 3.5,
"max": 25.30909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1113.0,
"min": 154.0,
"max": 1392.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.295454545454547,
"min": 3.5,
"max": 25.30909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1113.0,
"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": "1702125538",
"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": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1702126006"
},
"total": 467.76004401399996,
"count": 1,
"self": 0.43150075799985643,
"children": {
"run_training.setup": {
"total": 0.056221359000119264,
"count": 1,
"self": 0.056221359000119264
},
"TrainerController.start_learning": {
"total": 467.272321897,
"count": 1,
"self": 0.5557772480208314,
"children": {
"TrainerController._reset_env": {
"total": 3.5610262620000412,
"count": 1,
"self": 3.5610262620000412
},
"TrainerController.advance": {
"total": 463.0696915609792,
"count": 18199,
"self": 0.25975469098420945,
"children": {
"env_step": {
"total": 462.809936869995,
"count": 18199,
"self": 312.9429477379599,
"children": {
"SubprocessEnvManager._take_step": {
"total": 149.58100429703154,
"count": 18199,
"self": 1.4292762730215145,
"children": {
"TorchPolicy.evaluate": {
"total": 148.15172802401003,
"count": 18199,
"self": 148.15172802401003
}
}
},
"workers": {
"total": 0.2859848350035463,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 466.055406185998,
"count": 18199,
"is_parallel": true,
"self": 231.0654710269862,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005568805999928372,
"count": 1,
"is_parallel": true,
"self": 0.004114914999263419,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001453891000664953,
"count": 10,
"is_parallel": true,
"self": 0.001453891000664953
}
}
},
"UnityEnvironment.step": {
"total": 0.09231695299990861,
"count": 1,
"is_parallel": true,
"self": 0.0006714319997627172,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00036625500001719047,
"count": 1,
"is_parallel": true,
"self": 0.00036625500001719047
},
"communicator.exchange": {
"total": 0.08942021600000771,
"count": 1,
"is_parallel": true,
"self": 0.08942021600000771
},
"steps_from_proto": {
"total": 0.0018590500001209875,
"count": 1,
"is_parallel": true,
"self": 0.0003283800003828219,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015306699997381656,
"count": 10,
"is_parallel": true,
"self": 0.0015306699997381656
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 234.9899351590118,
"count": 18198,
"is_parallel": true,
"self": 10.350972599005672,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.295462340004406,
"count": 18198,
"is_parallel": true,
"self": 5.295462340004406
},
"communicator.exchange": {
"total": 186.39643189200297,
"count": 18198,
"is_parallel": true,
"self": 186.39643189200297
},
"steps_from_proto": {
"total": 32.94706832799875,
"count": 18198,
"is_parallel": true,
"self": 6.163619808032081,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.78344851996667,
"count": 181980,
"is_parallel": true,
"self": 26.78344851996667
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011722899989763391,
"count": 1,
"self": 0.00011722899989763391,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 459.1807053730208,
"count": 494091,
"is_parallel": true,
"self": 10.328730740007586,
"children": {
"process_trajectory": {
"total": 258.2319789270134,
"count": 494091,
"is_parallel": true,
"self": 257.7813008930136,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4506780339997931,
"count": 4,
"is_parallel": true,
"self": 0.4506780339997931
}
}
},
"_update_policy": {
"total": 190.61999570599983,
"count": 90,
"is_parallel": true,
"self": 59.8528288549976,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.76716685100223,
"count": 4587,
"is_parallel": true,
"self": 130.76716685100223
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08570959700000458,
"count": 1,
"self": 0.001036150999880192,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08467344600012439,
"count": 1,
"self": 0.08467344600012439
}
}
}
}
}
}
}