sunyizhe's picture
First Push
85c597b verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.671283483505249,
"min": 0.671283483505249,
"max": 2.8551721572875977,
"count": 40
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6793.388671875,
"min": 6766.7333984375,
"max": 29334.0390625,
"count": 40
},
"SnowballTarget.Step.mean": {
"value": 399992.0,
"min": 9952.0,
"max": 399992.0,
"count": 40
},
"SnowballTarget.Step.sum": {
"value": 399992.0,
"min": 9952.0,
"max": 399992.0,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.536530494689941,
"min": 0.38232892751693726,
"max": 13.536530494689941,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2639.62353515625,
"min": 74.17181396484375,
"max": 2764.867431640625,
"count": 40
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 40
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 40
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06891218573825122,
"min": 0.06035231877281595,
"max": 0.07357712436156968,
"count": 40
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2756487429530049,
"min": 0.2541918448713498,
"max": 0.3678856218078484,
"count": 40
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20755008213660298,
"min": 0.11188064633033185,
"max": 0.27622038640227975,
"count": 40
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8302003285464119,
"min": 0.4475225853213274,
"max": 1.3811019320113986,
"count": 40
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.891098702999994e-06,
"min": 3.891098702999994e-06,
"max": 0.000295941001353,
"count": 40
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.5564394811999976e-05,
"min": 1.5564394811999976e-05,
"max": 0.0014425800191399996,
"count": 40
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.101297,
"min": 0.101297,
"max": 0.19864700000000002,
"count": 40
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.405188,
"min": 0.405188,
"max": 0.98086,
"count": 40
},
"SnowballTarget.Policy.Beta.mean": {
"value": 7.472029999999992e-05,
"min": 7.472029999999992e-05,
"max": 0.004932485299999999,
"count": 40
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00029888119999999966,
"min": 0.00029888119999999966,
"max": 0.024044914,
"count": 40
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.272727272727273,
"min": 2.7954545454545454,
"max": 26.636363636363637,
"count": 40
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1156.0,
"min": 123.0,
"max": 1453.0,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.272727272727273,
"min": 2.7954545454545454,
"max": 26.636363636363637,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1156.0,
"min": 123.0,
"max": 1453.0,
"count": 40
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1760079582",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/midea/miniconda3/envs/mlagents/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./trained-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": "1760079830"
},
"total": 247.9133638619969,
"count": 1,
"self": 0.16706113000691403,
"children": {
"run_training.setup": {
"total": 0.010052138997707516,
"count": 1,
"self": 0.010052138997707516
},
"TrainerController.start_learning": {
"total": 247.7362505929923,
"count": 1,
"self": 0.36094217048957944,
"children": {
"TrainerController._reset_env": {
"total": 1.0889983889937866,
"count": 1,
"self": 1.0889983889937866
},
"TrainerController.advance": {
"total": 246.2644435625116,
"count": 36406,
"self": 0.16259597829775885,
"children": {
"env_step": {
"total": 246.10184758421383,
"count": 36406,
"self": 192.9602285788278,
"children": {
"SubprocessEnvManager._take_step": {
"total": 52.968842546702945,
"count": 36406,
"self": 0.8992591464630095,
"children": {
"TorchPolicy.evaluate": {
"total": 52.069583400239935,
"count": 36406,
"self": 52.069583400239935
}
}
},
"workers": {
"total": 0.17277645868307445,
"count": 36406,
"self": 0.0,
"children": {
"worker_root": {
"total": 247.29174592455092,
"count": 36406,
"is_parallel": true,
"self": 111.00157469685655,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010476330062374473,
"count": 1,
"is_parallel": true,
"self": 0.0005360460054362193,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000511587000801228,
"count": 10,
"is_parallel": true,
"self": 0.000511587000801228
}
}
},
"UnityEnvironment.step": {
"total": 0.012361138011328876,
"count": 1,
"is_parallel": true,
"self": 0.0001945100084412843,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022373699175659567,
"count": 1,
"is_parallel": true,
"self": 0.00022373699175659567
},
"communicator.exchange": {
"total": 0.011202346009667963,
"count": 1,
"is_parallel": true,
"self": 0.011202346009667963
},
"steps_from_proto": {
"total": 0.0007405450014630333,
"count": 1,
"is_parallel": true,
"self": 0.00019281501590739936,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005477299855556339,
"count": 10,
"is_parallel": true,
"self": 0.0005477299855556339
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 136.29017122769437,
"count": 36405,
"is_parallel": true,
"self": 5.291091711740592,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.249778789031552,
"count": 36405,
"is_parallel": true,
"self": 3.249778789031552
},
"communicator.exchange": {
"total": 110.22489306393254,
"count": 36405,
"is_parallel": true,
"self": 110.22489306393254
},
"steps_from_proto": {
"total": 17.524407662989688,
"count": 36405,
"is_parallel": true,
"self": 3.6486812596122036,
"children": {
"_process_rank_one_or_two_observation": {
"total": 13.875726403377485,
"count": 364050,
"is_parallel": true,
"self": 13.875726403377485
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011970500054303557,
"count": 1,
"self": 0.00011970500054303557,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 246.06271424946317,
"count": 191827,
"is_parallel": true,
"self": 1.3469592523615574,
"children": {
"process_trajectory": {
"total": 139.74374805303523,
"count": 191827,
"is_parallel": true,
"self": 139.28161252905556,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4621355239796685,
"count": 8,
"is_parallel": true,
"self": 0.4621355239796685
}
}
},
"_update_policy": {
"total": 104.97200694406638,
"count": 181,
"is_parallel": true,
"self": 23.82219970380538,
"children": {
"TorchPPOOptimizer.update": {
"total": 81.149807240261,
"count": 9228,
"is_parallel": true,
"self": 81.149807240261
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.021746765996795148,
"count": 1,
"self": 0.00026043599063996226,
"children": {
"RLTrainer._checkpoint": {
"total": 0.021486330006155185,
"count": 1,
"self": 0.021486330006155185
}
}
}
}
}
}
}