amit-huggingface2's picture
First Push
e1dc1d2 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6451561450958252,
"min": 0.6286781430244446,
"max": 2.8756980895996094,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6585.75390625,
"min": 5853.9853515625,
"max": 29852.865234375,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499912.0,
"min": 9952.0,
"max": 499912.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499912.0,
"min": 9952.0,
"max": 499912.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.346131324768066,
"min": 0.3838321566581726,
"max": 13.421761512756348,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1347.959228515625,
"min": 37.231719970703125,
"max": 1372.527099609375,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.245283018867923,
"min": 3.3181818181818183,
"max": 26.636363636363637,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1391.0,
"min": 146.0,
"max": 1465.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.245283018867923,
"min": 3.3181818181818183,
"max": 26.636363636363637,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1391.0,
"min": 146.0,
"max": 1465.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06964334745151814,
"min": 0.061930045465352114,
"max": 0.07796469195654579,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.34821673725759067,
"min": 0.25014667038586225,
"max": 0.38377857424190964,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18812478988193998,
"min": 0.1348829431568875,
"max": 0.29769709139477973,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9406239494096998,
"min": 0.53953177262755,
"max": 1.4884854569738986,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.000099000000001e-06,
"min": 1.000099000000001e-06,
"max": 9.890000109999999e-05,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.0004950000000045e-06,
"min": 5.0004950000000045e-06,
"max": 0.00048460001540000003,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.101,
"min": 0.101,
"max": 0.19890000000000002,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.505,
"min": 0.41192000000000006,
"max": 0.9846000000000001,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 5.9900000000000047e-05,
"min": 5.9900000000000047e-05,
"max": 0.00494511,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00029950000000000023,
"min": 0.00029950000000000023,
"max": 0.024231540000000003,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1746728086",
"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 --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1746729194"
},
"total": 1107.603658034,
"count": 1,
"self": 0.43907356799945774,
"children": {
"run_training.setup": {
"total": 0.021276195000154985,
"count": 1,
"self": 0.021276195000154985
},
"TrainerController.start_learning": {
"total": 1107.1433082710005,
"count": 1,
"self": 1.000585237999985,
"children": {
"TrainerController._reset_env": {
"total": 2.0653975459999856,
"count": 1,
"self": 2.0653975459999856
},
"TrainerController.advance": {
"total": 1103.9625112460003,
"count": 45528,
"self": 1.0190705160430298,
"children": {
"env_step": {
"total": 782.389772776025,
"count": 45528,
"self": 592.5068356929787,
"children": {
"SubprocessEnvManager._take_step": {
"total": 189.3150668580315,
"count": 45528,
"self": 3.3085044539170667,
"children": {
"TorchPolicy.evaluate": {
"total": 186.00656240411445,
"count": 45528,
"self": 186.00656240411445
}
}
},
"workers": {
"total": 0.567870225014758,
"count": 45528,
"self": 0.0,
"children": {
"worker_root": {
"total": 1103.6144141670084,
"count": 45528,
"is_parallel": true,
"self": 584.7007441641026,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0025877699999909964,
"count": 1,
"is_parallel": true,
"self": 0.000841334000142524,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017464359998484724,
"count": 10,
"is_parallel": true,
"self": 0.0017464359998484724
}
}
},
"UnityEnvironment.step": {
"total": 0.036133436000000074,
"count": 1,
"is_parallel": true,
"self": 0.0005638149996229913,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003900700003214297,
"count": 1,
"is_parallel": true,
"self": 0.0003900700003214297
},
"communicator.exchange": {
"total": 0.03342848400006915,
"count": 1,
"is_parallel": true,
"self": 0.03342848400006915
},
"steps_from_proto": {
"total": 0.0017510669999865058,
"count": 1,
"is_parallel": true,
"self": 0.00035100400009469013,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014000629998918157,
"count": 10,
"is_parallel": true,
"self": 0.0014000629998918157
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 518.9136700029057,
"count": 45527,
"is_parallel": true,
"self": 24.4672301069686,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 13.899344948092676,
"count": 45527,
"is_parallel": true,
"self": 13.899344948092676
},
"communicator.exchange": {
"total": 398.9947476699763,
"count": 45527,
"is_parallel": true,
"self": 398.9947476699763
},
"steps_from_proto": {
"total": 81.5523472778682,
"count": 45527,
"is_parallel": true,
"self": 14.71189978594748,
"children": {
"_process_rank_one_or_two_observation": {
"total": 66.84044749192071,
"count": 455270,
"is_parallel": true,
"self": 66.84044749192071
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 320.5536679539323,
"count": 45528,
"self": 1.1939517788146077,
"children": {
"process_trajectory": {
"total": 61.22596244312717,
"count": 45528,
"self": 59.80232532412765,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4236371189995225,
"count": 10,
"self": 1.4236371189995225
}
}
},
"_update_policy": {
"total": 258.1337537319905,
"count": 227,
"self": 98.05847612397702,
"children": {
"TorchPPOOptimizer.update": {
"total": 160.0752776080135,
"count": 11577,
"self": 160.0752776080135
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.859997251420282e-07,
"count": 1,
"self": 8.859997251420282e-07
},
"TrainerController._save_models": {
"total": 0.11481335500047862,
"count": 1,
"self": 0.0015698730012445594,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11324348199923406,
"count": 1,
"self": 0.11324348199923406
}
}
}
}
}
}
}