georgao's picture
First Push
f8c37ff
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1260961294174194,
"min": 1.1260961294174194,
"max": 2.868818998336792,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10813.9013671875,
"min": 10813.9013671875,
"max": 29348.01953125,
"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": 11.287300109863281,
"min": 0.3153650164604187,
"max": 11.287300109863281,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2201.0234375,
"min": 61.18081283569336,
"max": 2247.860595703125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06936628880651494,
"min": 0.06504358894730389,
"max": 0.07530233062575195,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27746515522605975,
"min": 0.26017435578921555,
"max": 0.36285843285355335,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20467556852336025,
"min": 0.1101647904913133,
"max": 0.28417761280548337,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.818702274093441,
"min": 0.4406591619652532,
"max": 1.2863870377049726,
"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": 22.704545454545453,
"min": 3.272727272727273,
"max": 22.704545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 999.0,
"min": 144.0,
"max": 1229.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 22.704545454545453,
"min": 3.272727272727273,
"max": 22.704545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 999.0,
"min": 144.0,
"max": 1229.0,
"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": "1683509582",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1683510039"
},
"total": 457.441631378,
"count": 1,
"self": 0.7420246360000533,
"children": {
"run_training.setup": {
"total": 0.03629874799997879,
"count": 1,
"self": 0.03629874799997879
},
"TrainerController.start_learning": {
"total": 456.663307994,
"count": 1,
"self": 0.5744120100045507,
"children": {
"TrainerController._reset_env": {
"total": 3.865670614999999,
"count": 1,
"self": 3.865670614999999
},
"TrainerController.advance": {
"total": 452.01265301799555,
"count": 18218,
"self": 0.262673679991849,
"children": {
"env_step": {
"total": 451.7499793380037,
"count": 18218,
"self": 330.18501791501023,
"children": {
"SubprocessEnvManager._take_step": {
"total": 121.29657307899657,
"count": 18218,
"self": 1.8831184769932179,
"children": {
"TorchPolicy.evaluate": {
"total": 119.41345460200336,
"count": 18218,
"self": 119.41345460200336
}
}
},
"workers": {
"total": 0.2683883439968895,
"count": 18218,
"self": 0.0,
"children": {
"worker_root": {
"total": 455.04718505599635,
"count": 18218,
"is_parallel": true,
"self": 210.8004722299961,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004756469999961155,
"count": 1,
"is_parallel": true,
"self": 0.0034253899999043824,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013310800000567724,
"count": 10,
"is_parallel": true,
"self": 0.0013310800000567724
}
}
},
"UnityEnvironment.step": {
"total": 0.034745466000003944,
"count": 1,
"is_parallel": true,
"self": 0.0005578189999368988,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003855280000379935,
"count": 1,
"is_parallel": true,
"self": 0.0003855280000379935
},
"communicator.exchange": {
"total": 0.031998907000001964,
"count": 1,
"is_parallel": true,
"self": 0.031998907000001964
},
"steps_from_proto": {
"total": 0.001803212000027088,
"count": 1,
"is_parallel": true,
"self": 0.0003563870000675706,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014468249999595173,
"count": 10,
"is_parallel": true,
"self": 0.0014468249999595173
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 244.24671282600025,
"count": 18217,
"is_parallel": true,
"self": 9.488998456010052,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.185534067997878,
"count": 18217,
"is_parallel": true,
"self": 5.185534067997878
},
"communicator.exchange": {
"total": 197.71936472299637,
"count": 18217,
"is_parallel": true,
"self": 197.71936472299637
},
"steps_from_proto": {
"total": 31.852815578995944,
"count": 18217,
"is_parallel": true,
"self": 6.104110066015835,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.74870551298011,
"count": 182170,
"is_parallel": true,
"self": 25.74870551298011
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.383199997297197e-05,
"count": 1,
"self": 8.383199997297197e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 448.83194856697344,
"count": 409039,
"is_parallel": true,
"self": 8.942322433013771,
"children": {
"process_trajectory": {
"total": 248.50761655995916,
"count": 409039,
"is_parallel": true,
"self": 247.30112937695918,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2064871829999788,
"count": 4,
"is_parallel": true,
"self": 1.2064871829999788
}
}
},
"_update_policy": {
"total": 191.3820095740005,
"count": 90,
"is_parallel": true,
"self": 72.36578395899727,
"children": {
"TorchPPOOptimizer.update": {
"total": 119.01622561500324,
"count": 4587,
"is_parallel": true,
"self": 119.01622561500324
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.2104885189999095,
"count": 1,
"self": 0.0011150819999556916,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2093734369999538,
"count": 1,
"self": 0.2093734369999538
}
}
}
}
}
}
}