Nikara3's picture
First SnowballTarget
73f6286 verified
Raw
History Blame Contribute Delete
17.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9198804497718811,
"min": 0.9198804497718811,
"max": 2.8791849613189697,
"count": 40
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9390.1396484375,
"min": 8857.474609375,
"max": 29390.720703125,
"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": 13.276655197143555,
"min": 0.1431470662355423,
"max": 13.276655197143555,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2588.94775390625,
"min": 27.770530700683594,
"max": 2721.47998046875,
"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.Environment.CumulativeReward.mean": {
"value": 25.704545454545453,
"min": 2.840909090909091,
"max": 26.163636363636364,
"count": 40
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1131.0,
"min": 125.0,
"max": 1439.0,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.704545454545453,
"min": 2.840909090909091,
"max": 26.163636363636364,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1131.0,
"min": 125.0,
"max": 1439.0,
"count": 40
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.04926017627654159,
"min": 0.03366512105290609,
"max": 0.05385013396267359,
"count": 40
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.09852035255308318,
"min": 0.06733024210581218,
"max": 0.1559599547637809,
"count": 40
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20272864985699746,
"min": 0.09988021931163601,
"max": 0.3170539654937445,
"count": 40
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.4054572997139949,
"min": 0.19976043862327203,
"max": 0.8811593993621714,
"count": 40
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 4.716098428000004e-06,
"min": 4.716098428000004e-06,
"max": 0.000295116001628,
"count": 40
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 9.432196856000007e-06,
"min": 9.432196856000007e-06,
"max": 0.000820998026334,
"count": 40
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.101572,
"min": 0.101572,
"max": 0.198372,
"count": 40
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.203144,
"min": 0.203144,
"max": 0.5736660000000001,
"count": 40
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00016704280000000014,
"min": 0.00016704280000000014,
"max": 0.009837362799999999,
"count": 40
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0003340856000000003,
"min": 0.0003340856000000003,
"max": 0.027369233399999998,
"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": "1781878963",
"python_version": "3.10.11 (main, May 16 2023, 00:28:57) [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=SnowballTarget --no-graphics --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1781879858"
},
"total": 895.1481593630006,
"count": 1,
"self": 0.47975032800150075,
"children": {
"run_training.setup": {
"total": 0.025792601999455655,
"count": 1,
"self": 0.025792601999455655
},
"TrainerController.start_learning": {
"total": 894.6426164329996,
"count": 1,
"self": 0.8465098429505815,
"children": {
"TrainerController._reset_env": {
"total": 3.352838435999729,
"count": 1,
"self": 3.352838435999729
},
"TrainerController.advance": {
"total": 890.3429854080496,
"count": 36392,
"self": 0.8370579119591639,
"children": {
"env_step": {
"total": 694.776734165067,
"count": 36392,
"self": 541.9789595850452,
"children": {
"SubprocessEnvManager._take_step": {
"total": 152.31134096096412,
"count": 36392,
"self": 2.6836279059680237,
"children": {
"TorchPolicy.evaluate": {
"total": 149.6277130549961,
"count": 36392,
"self": 149.6277130549961
}
}
},
"workers": {
"total": 0.48643361905760685,
"count": 36392,
"self": 0.0,
"children": {
"worker_root": {
"total": 891.3768026259713,
"count": 36392,
"is_parallel": true,
"self": 416.000136784035,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006089792000238958,
"count": 1,
"is_parallel": true,
"self": 0.004051651000736456,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020381409995025024,
"count": 10,
"is_parallel": true,
"self": 0.0020381409995025024
}
}
},
"UnityEnvironment.step": {
"total": 0.04146721799952502,
"count": 1,
"is_parallel": true,
"self": 0.0006207870001162519,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041833599971141666,
"count": 1,
"is_parallel": true,
"self": 0.00041833599971141666
},
"communicator.exchange": {
"total": 0.03798488699976588,
"count": 1,
"is_parallel": true,
"self": 0.03798488699976588
},
"steps_from_proto": {
"total": 0.0024432079999314738,
"count": 1,
"is_parallel": true,
"self": 0.0004036010004710988,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002039606999460375,
"count": 10,
"is_parallel": true,
"self": 0.002039606999460375
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 475.3766658419363,
"count": 36391,
"is_parallel": true,
"self": 21.443915279868634,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 11.519735307944757,
"count": 36391,
"is_parallel": true,
"self": 11.519735307944757
},
"communicator.exchange": {
"total": 364.13160759907896,
"count": 36391,
"is_parallel": true,
"self": 364.13160759907896
},
"steps_from_proto": {
"total": 78.28140765504395,
"count": 36391,
"is_parallel": true,
"self": 13.707899776940394,
"children": {
"_process_rank_one_or_two_observation": {
"total": 64.57350787810356,
"count": 363910,
"is_parallel": true,
"self": 64.57350787810356
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 194.72919333102345,
"count": 36392,
"self": 1.028993670053751,
"children": {
"process_trajectory": {
"total": 50.6316608809675,
"count": 36392,
"self": 49.846397487968716,
"children": {
"RLTrainer._checkpoint": {
"total": 0.785263392998786,
"count": 8,
"self": 0.785263392998786
}
}
},
"_update_policy": {
"total": 143.0685387800022,
"count": 90,
"self": 79.50791408401437,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.560624695987826,
"count": 4587,
"self": 63.560624695987826
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1299998732283711e-06,
"count": 1,
"self": 1.1299998732283711e-06
},
"TrainerController._save_models": {
"total": 0.10028161599984742,
"count": 1,
"self": 0.0011432789997343207,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0991383370001131,
"count": 1,
"self": 0.0991383370001131
}
}
}
}
}
}
}