greg-szopinski's picture
First Push
5ec61d5
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.5861135125160217,
"min": 0.5861135125160217,
"max": 0.7885019183158875,
"count": 25
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 5570.4228515625,
"min": 5570.4228515625,
"max": 8083.7216796875,
"count": 25
},
"SnowballTarget.Step.mean": {
"value": 499952.0,
"min": 259960.0,
"max": 499952.0,
"count": 25
},
"SnowballTarget.Step.sum": {
"value": 499952.0,
"min": 259960.0,
"max": 499952.0,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.575894355773926,
"min": 13.104690551757812,
"max": 13.738127708435059,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2647.29931640625,
"min": 2544.199951171875,
"max": 2802.578125,
"count": 25
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 25
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 25
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07453375356443062,
"min": 0.06279630234908551,
"max": 0.07516275822988473,
"count": 25
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2981350142577225,
"min": 0.25118520939634204,
"max": 0.37581379114942365,
"count": 25
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18462860503909634,
"min": 0.1643054305995796,
"max": 0.23153529864023714,
"count": 25
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7385144201563854,
"min": 0.6572217223983184,
"max": 0.9672914010052587,
"count": 25
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.912099043999997e-06,
"min": 1.912099043999997e-06,
"max": 9.783205108399998e-05,
"count": 25
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 7.648396175999987e-06,
"min": 7.648396175999987e-06,
"max": 0.00046936026532,
"count": 25
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.100956,
"min": 0.100956,
"max": 0.14891600000000002,
"count": 25
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.403824,
"min": 0.403824,
"max": 0.73468,
"count": 25
},
"SnowballTarget.Policy.Beta.mean": {
"value": 5.770439999999993e-05,
"min": 5.770439999999993e-05,
"max": 0.0024509084,
"count": 25
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0002308175999999997,
"min": 0.0002308175999999997,
"max": 0.011760532,
"count": 25
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.045454545454547,
"min": 25.654545454545456,
"max": 27.132075471698112,
"count": 25
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1146.0,
"min": 1135.0,
"max": 1465.0,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.045454545454547,
"min": 25.654545454545456,
"max": 27.132075471698112,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1146.0,
"min": 1135.0,
"max": 1465.0,
"count": 25
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 25
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 25
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1690818090",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
"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": "1690818873"
},
"total": 783.0092075910002,
"count": 1,
"self": 0.5486062180004865,
"children": {
"run_training.setup": {
"total": 0.03929821299993819,
"count": 1,
"self": 0.03929821299993819
},
"TrainerController.start_learning": {
"total": 782.4213031599998,
"count": 1,
"self": 1.0134433219679977,
"children": {
"TrainerController._reset_env": {
"total": 4.7076938610000525,
"count": 1,
"self": 4.7076938610000525
},
"TrainerController.advance": {
"total": 776.5165083500319,
"count": 22738,
"self": 0.5035808390323382,
"children": {
"env_step": {
"total": 776.0129275109996,
"count": 22738,
"self": 563.9557182620367,
"children": {
"SubprocessEnvManager._take_step": {
"total": 211.56079424597442,
"count": 22738,
"self": 3.2127091859663324,
"children": {
"TorchPolicy.evaluate": {
"total": 208.3480850600081,
"count": 22738,
"self": 208.3480850600081
}
}
},
"workers": {
"total": 0.4964150029884422,
"count": 22738,
"self": 0.0,
"children": {
"worker_root": {
"total": 779.5726080059665,
"count": 22738,
"is_parallel": true,
"self": 363.26295899294564,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003498176999983116,
"count": 1,
"is_parallel": true,
"self": 0.001385029999710241,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021131470002728747,
"count": 10,
"is_parallel": true,
"self": 0.0021131470002728747
}
}
},
"UnityEnvironment.step": {
"total": 0.08763165499999559,
"count": 1,
"is_parallel": true,
"self": 0.0007529249996878207,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047507300018878595,
"count": 1,
"is_parallel": true,
"self": 0.00047507300018878595
},
"communicator.exchange": {
"total": 0.07482427700006156,
"count": 1,
"is_parallel": true,
"self": 0.07482427700006156
},
"steps_from_proto": {
"total": 0.011579380000057427,
"count": 1,
"is_parallel": true,
"self": 0.0006169990006128501,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.010962380999444576,
"count": 10,
"is_parallel": true,
"self": 0.010962380999444576
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 416.3096490130208,
"count": 22737,
"is_parallel": true,
"self": 17.84923510403928,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.948606663981309,
"count": 22737,
"is_parallel": true,
"self": 8.948606663981309
},
"communicator.exchange": {
"total": 331.5578706680376,
"count": 22737,
"is_parallel": true,
"self": 331.5578706680376
},
"steps_from_proto": {
"total": 57.95393657696263,
"count": 22737,
"is_parallel": true,
"self": 11.618623971895659,
"children": {
"_process_rank_one_or_two_observation": {
"total": 46.335312605066974,
"count": 227370,
"is_parallel": true,
"self": 46.335312605066974
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.4904999867867446e-05,
"count": 1,
"self": 4.4904999867867446e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 769.1780761492009,
"count": 760649,
"is_parallel": true,
"self": 18.953796414831913,
"children": {
"process_trajectory": {
"total": 424.62607131036884,
"count": 760649,
"is_parallel": true,
"self": 422.69075856136897,
"children": {
"RLTrainer._checkpoint": {
"total": 1.935312748999877,
"count": 5,
"is_parallel": true,
"self": 1.935312748999877
}
}
},
"_update_policy": {
"total": 325.5982084240002,
"count": 113,
"is_parallel": true,
"self": 118.91411360801203,
"children": {
"TorchPPOOptimizer.update": {
"total": 206.68409481598815,
"count": 5760,
"is_parallel": true,
"self": 206.68409481598815
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.18361272199990708,
"count": 1,
"self": 0.0014558739999301906,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1821568479999769,
"count": 1,
"self": 0.1821568479999769
}
}
}
}
}
}
}