granenko's picture
First Push
5105c4a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1591025590896606,
"min": 1.1591025590896606,
"max": 2.8643639087677,
"count": 17
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 11118.111328125,
"min": 11118.111328125,
"max": 29239.427734375,
"count": 17
},
"SnowballTarget.Step.mean": {
"value": 169976.0,
"min": 9952.0,
"max": 169976.0,
"count": 17
},
"SnowballTarget.Step.sum": {
"value": 169976.0,
"min": 9952.0,
"max": 169976.0,
"count": 17
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.330113410949707,
"min": 0.6275967359542847,
"max": 12.330113410949707,
"count": 17
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2527.67333984375,
"min": 121.7537612915039,
"max": 2527.67333984375,
"count": 17
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06710609917876462,
"min": 0.06406728350203576,
"max": 0.0757081382069052,
"count": 17
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.33553049589382306,
"min": 0.25626913400814305,
"max": 0.37090685595210426,
"count": 17
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21298438556054058,
"min": 0.11686520335406028,
"max": 0.28211189222102073,
"count": 17
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.064921927802703,
"min": 0.4674608134162411,
"max": 1.4105594611051038,
"count": 17
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.978920536470583e-06,
"min": 8.978920536470583e-06,
"max": 0.0002904494149482353,
"count": 17
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 4.489460268235292e-05,
"min": 4.489460268235292e-05,
"max": 0.0013648941626823526,
"count": 17
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10299294117647059,
"min": 0.10299294117647059,
"max": 0.19681647058823531,
"count": 17
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.514964705882353,
"min": 0.4352658823529413,
"max": 0.954964705882353,
"count": 17
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00015934776470588233,
"min": 0.00015934776470588233,
"max": 0.004841141882352941,
"count": 17
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0007967388235294116,
"min": 0.0007967388235294116,
"max": 0.022752738823529413,
"count": 17
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 17
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 17
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.527272727272727,
"min": 3.090909090909091,
"max": 24.75,
"count": 17
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1349.0,
"min": 136.0,
"max": 1349.0,
"count": 17
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.527272727272727,
"min": 3.090909090909091,
"max": 24.75,
"count": 17
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1349.0,
"min": 136.0,
"max": 1349.0,
"count": 17
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 17
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 17
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1757957599",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1757957971"
},
"total": 371.278641158,
"count": 1,
"self": 0.42972936900014247,
"children": {
"run_training.setup": {
"total": 0.025705669999979364,
"count": 1,
"self": 0.025705669999979364
},
"TrainerController.start_learning": {
"total": 370.8232061189999,
"count": 1,
"self": 0.3443921460011552,
"children": {
"TrainerController._reset_env": {
"total": 3.1064313079998556,
"count": 1,
"self": 3.1064313079998556
},
"TrainerController.advance": {
"total": 367.27709929299886,
"count": 15464,
"self": 0.3324291569788329,
"children": {
"env_step": {
"total": 261.510216093008,
"count": 15464,
"self": 201.30239721599833,
"children": {
"SubprocessEnvManager._take_step": {
"total": 60.00797852400865,
"count": 15464,
"self": 1.1016091830081223,
"children": {
"TorchPolicy.evaluate": {
"total": 58.90636934100053,
"count": 15464,
"self": 58.90636934100053
}
}
},
"workers": {
"total": 0.19984035300103642,
"count": 15464,
"self": 0.0,
"children": {
"worker_root": {
"total": 369.6811520329859,
"count": 15464,
"is_parallel": true,
"self": 193.15463715097917,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005853120999972816,
"count": 1,
"is_parallel": true,
"self": 0.004337254000347457,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015158669996253593,
"count": 10,
"is_parallel": true,
"self": 0.0015158669996253593
}
}
},
"UnityEnvironment.step": {
"total": 0.03503240999998525,
"count": 1,
"is_parallel": true,
"self": 0.0005408750000697182,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003927990001102444,
"count": 1,
"is_parallel": true,
"self": 0.0003927990001102444
},
"communicator.exchange": {
"total": 0.0322879779998857,
"count": 1,
"is_parallel": true,
"self": 0.0322879779998857
},
"steps_from_proto": {
"total": 0.0018107579999195877,
"count": 1,
"is_parallel": true,
"self": 0.00033934099974430865,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001471417000175279,
"count": 10,
"is_parallel": true,
"self": 0.001471417000175279
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 176.52651488200672,
"count": 15463,
"is_parallel": true,
"self": 8.31920321898997,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.505316354989645,
"count": 15463,
"is_parallel": true,
"self": 4.505316354989645
},
"communicator.exchange": {
"total": 137.16799236901807,
"count": 15463,
"is_parallel": true,
"self": 137.16799236901807
},
"steps_from_proto": {
"total": 26.534002939009042,
"count": 15463,
"is_parallel": true,
"self": 4.745211895038665,
"children": {
"_process_rank_one_or_two_observation": {
"total": 21.788791043970377,
"count": 154630,
"is_parallel": true,
"self": 21.788791043970377
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 105.43445404301201,
"count": 15464,
"self": 0.4443695120191933,
"children": {
"process_trajectory": {
"total": 23.028450066994083,
"count": 15464,
"self": 22.281292824993443,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7471572420006396,
"count": 8,
"self": 0.7471572420006396
}
}
},
"_update_policy": {
"total": 81.96163446399873,
"count": 77,
"self": 33.54951859100561,
"children": {
"TorchPPOOptimizer.update": {
"total": 48.41211587299313,
"count": 3924,
"self": 48.41211587299313
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.639999578008428e-07,
"count": 1,
"self": 8.639999578008428e-07
},
"TrainerController._save_models": {
"total": 0.09528250800008209,
"count": 1,
"self": 0.0009033930000441615,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09437911500003793,
"count": 1,
"self": 0.09437911500003793
}
}
}
}
}
}
}