mgmeskill's picture
First Push
0601dab
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8901045322418213,
"min": 0.8901045322418213,
"max": 2.863952875137329,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8567.255859375,
"min": 8567.255859375,
"max": 29298.23828125,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.845795631408691,
"min": 0.4657001793384552,
"max": 12.845795631408691,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2504.93017578125,
"min": 90.34583282470703,
"max": 2607.5322265625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0727478230877679,
"min": 0.06409031119954878,
"max": 0.07291633003076319,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2909912923510716,
"min": 0.2563612447981951,
"max": 0.36458165015381594,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19535254029666677,
"min": 0.13246458564547128,
"max": 0.26096101638440994,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7814101611866671,
"min": 0.5298583425818851,
"max": 1.2880778064695644,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.204545454545453,
"min": 3.4545454545454546,
"max": 25.522727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1109.0,
"min": 152.0,
"max": 1391.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.204545454545453,
"min": 3.4545454545454546,
"max": 25.522727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1109.0,
"min": 152.0,
"max": 1391.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1691107548",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"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": "1691108044"
},
"total": 496.14109490299995,
"count": 1,
"self": 0.7321856599999705,
"children": {
"run_training.setup": {
"total": 0.043274435999990146,
"count": 1,
"self": 0.043274435999990146
},
"TrainerController.start_learning": {
"total": 495.365634807,
"count": 1,
"self": 0.562652545001697,
"children": {
"TrainerController._reset_env": {
"total": 5.374514479999959,
"count": 1,
"self": 5.374514479999959
},
"TrainerController.advance": {
"total": 489.1850327569983,
"count": 18224,
"self": 0.2770578190045967,
"children": {
"env_step": {
"total": 488.9079749379937,
"count": 18224,
"self": 351.70590521899425,
"children": {
"SubprocessEnvManager._take_step": {
"total": 136.91793164100392,
"count": 18224,
"self": 1.7697697399983667,
"children": {
"TorchPolicy.evaluate": {
"total": 135.14816190100555,
"count": 18224,
"self": 135.14816190100555
}
}
},
"workers": {
"total": 0.2841380779955216,
"count": 18224,
"self": 0.0,
"children": {
"worker_root": {
"total": 493.6353454130005,
"count": 18224,
"is_parallel": true,
"self": 240.07164777400044,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006275288000040291,
"count": 1,
"is_parallel": true,
"self": 0.004369701000086934,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001905586999953357,
"count": 10,
"is_parallel": true,
"self": 0.001905586999953357
}
}
},
"UnityEnvironment.step": {
"total": 0.07450327499998366,
"count": 1,
"is_parallel": true,
"self": 0.0007055699999796161,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000332683999999972,
"count": 1,
"is_parallel": true,
"self": 0.000332683999999972
},
"communicator.exchange": {
"total": 0.06610936599997785,
"count": 1,
"is_parallel": true,
"self": 0.06610936599997785
},
"steps_from_proto": {
"total": 0.007355655000026218,
"count": 1,
"is_parallel": true,
"self": 0.00043856400020558794,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00691709099982063,
"count": 10,
"is_parallel": true,
"self": 0.00691709099982063
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 253.56369763900005,
"count": 18223,
"is_parallel": true,
"self": 10.801431420998085,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.331885256003659,
"count": 18223,
"is_parallel": true,
"self": 5.331885256003659
},
"communicator.exchange": {
"total": 200.52514041199748,
"count": 18223,
"is_parallel": true,
"self": 200.52514041199748
},
"steps_from_proto": {
"total": 36.905240550000826,
"count": 18223,
"is_parallel": true,
"self": 6.62783860501338,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.277401944987446,
"count": 182230,
"is_parallel": true,
"self": 30.277401944987446
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015854100001888582,
"count": 1,
"self": 0.00015854100001888582,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 485.6888049249817,
"count": 417048,
"is_parallel": true,
"self": 9.532304662951674,
"children": {
"process_trajectory": {
"total": 273.07086960303087,
"count": 417048,
"is_parallel": true,
"self": 241.1261173110309,
"children": {
"RLTrainer._checkpoint": {
"total": 31.944752291999976,
"count": 100,
"is_parallel": true,
"self": 31.944752291999976
}
}
},
"_update_policy": {
"total": 203.08563065899915,
"count": 90,
"is_parallel": true,
"self": 82.02733038199767,
"children": {
"TorchPPOOptimizer.update": {
"total": 121.05830027700148,
"count": 4578,
"is_parallel": true,
"self": 121.05830027700148
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.24327648400003454,
"count": 1,
"self": 0.0011748690000104034,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24210161500002414,
"count": 1,
"self": 0.24210161500002414
}
}
}
}
}
}
}