kenlui's picture
First Push
c5d8b31
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1829121112823486,
"min": 1.1829121112823486,
"max": 2.8903541564941406,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 11398.541015625,
"min": 10787.076171875,
"max": 29600.1171875,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.20389175415039,
"min": -0.02847709320485592,
"max": 13.20389175415039,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2706.7978515625,
"min": -5.5245561599731445,
"max": 2706.7978515625,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.2,
"min": 2.909090909090909,
"max": 27.272727272727273,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1441.0,
"min": 128.0,
"max": 1458.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.2,
"min": 2.909090909090909,
"max": 27.272727272727273,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1441.0,
"min": 128.0,
"max": 1458.0,
"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
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.03379655620723497,
"min": 0.02876835135553847,
"max": 0.041196556116587346,
"count": 47
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.03379655620723497,
"min": 0.02876835135553847,
"max": 0.041196556116587346,
"count": 47
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17735335379838943,
"min": 0.08391845673322677,
"max": 0.3003501319885254,
"count": 47
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.17735335379838943,
"min": 0.08391845673322677,
"max": 0.3003501319885254,
"count": 47
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 5.217698260799988e-06,
"min": 5.217698260799988e-06,
"max": 0.00029376000207999997,
"count": 47
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.217698260799988e-06,
"min": 5.217698260799988e-06,
"max": 0.00029376000207999997,
"count": 47
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10173920000000003,
"min": 0.10173920000000003,
"max": 0.19792,
"count": 47
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.10173920000000003,
"min": 0.10173920000000003,
"max": 0.19792,
"count": 47
},
"SnowballTarget.Policy.Beta.mean": {
"value": 9.678607999999982e-05,
"min": 9.678607999999982e-05,
"max": 0.004896208,
"count": 47
},
"SnowballTarget.Policy.Beta.sum": {
"value": 9.678607999999982e-05,
"min": 9.678607999999982e-05,
"max": 0.004896208,
"count": 47
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1683709967",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --torch-device cuda:0",
"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": "1683711194"
},
"total": 1226.9367471220003,
"count": 1,
"self": 0.4317686700005652,
"children": {
"run_training.setup": {
"total": 0.04150484900003448,
"count": 1,
"self": 0.04150484900003448
},
"TrainerController.start_learning": {
"total": 1226.4634736029998,
"count": 1,
"self": 1.3826260769917553,
"children": {
"TrainerController._reset_env": {
"total": 3.9375089719999323,
"count": 1,
"self": 3.9375089719999323
},
"TrainerController.advance": {
"total": 1220.931010805008,
"count": 45481,
"self": 0.6395590950157839,
"children": {
"env_step": {
"total": 1220.2914517099923,
"count": 45481,
"self": 917.3393176769689,
"children": {
"SubprocessEnvManager._take_step": {
"total": 302.28921457000797,
"count": 45481,
"self": 4.59240423601068,
"children": {
"TorchPolicy.evaluate": {
"total": 297.6968103339973,
"count": 45481,
"self": 297.6968103339973
}
}
},
"workers": {
"total": 0.6629194630154416,
"count": 45481,
"self": 0.0,
"children": {
"worker_root": {
"total": 1222.8967919990082,
"count": 45481,
"is_parallel": true,
"self": 612.8191297570006,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00474080200001481,
"count": 1,
"is_parallel": true,
"self": 0.0033298570001534245,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014109449998613854,
"count": 10,
"is_parallel": true,
"self": 0.0014109449998613854
}
}
},
"UnityEnvironment.step": {
"total": 0.03601872399997319,
"count": 1,
"is_parallel": true,
"self": 0.00040407299991329637,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003200849999984712,
"count": 1,
"is_parallel": true,
"self": 0.0003200849999984712
},
"communicator.exchange": {
"total": 0.033237880000001496,
"count": 1,
"is_parallel": true,
"self": 0.033237880000001496
},
"steps_from_proto": {
"total": 0.0020566860000599263,
"count": 1,
"is_parallel": true,
"self": 0.00037323400010791374,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016834519999520126,
"count": 10,
"is_parallel": true,
"self": 0.0016834519999520126
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 610.0776622420076,
"count": 45480,
"is_parallel": true,
"self": 24.159627008996722,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 12.885120171974563,
"count": 45480,
"is_parallel": true,
"self": 12.885120171974563
},
"communicator.exchange": {
"total": 491.87385374302755,
"count": 45480,
"is_parallel": true,
"self": 491.87385374302755
},
"steps_from_proto": {
"total": 81.15906131800875,
"count": 45480,
"is_parallel": true,
"self": 15.44662656403682,
"children": {
"_process_rank_one_or_two_observation": {
"total": 65.71243475397193,
"count": 454800,
"is_parallel": true,
"self": 65.71243475397193
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012070299999322742,
"count": 1,
"self": 0.00012070299999322742,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1208.2224627998933,
"count": 1431320,
"is_parallel": true,
"self": 33.256331730968895,
"children": {
"process_trajectory": {
"total": 822.943776247924,
"count": 1431320,
"is_parallel": true,
"self": 819.127956742924,
"children": {
"RLTrainer._checkpoint": {
"total": 3.815819505000036,
"count": 10,
"is_parallel": true,
"self": 3.815819505000036
}
}
},
"_update_policy": {
"total": 352.02235482100036,
"count": 47,
"is_parallel": true,
"self": 238.92269794601248,
"children": {
"TorchPPOOptimizer.update": {
"total": 113.09965687498789,
"count": 4760,
"is_parallel": true,
"self": 113.09965687498789
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.21220704600000317,
"count": 1,
"self": 0.0027471619998777896,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20945988400012538,
"count": 1,
"self": 0.20945988400012538
}
}
}
}
}
}
}