{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.897433876991272,
"min": 0.897433876991272,
"max": 2.864539861679077,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8637.80078125,
"min": 8637.80078125,
"max": 29461.79296875,
"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": 13.061488151550293,
"min": 0.5178958177566528,
"max": 13.061488151550293,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2546.990234375,
"min": 100.47178649902344,
"max": 2644.28955078125,
"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": 0.07168507664505787,
"min": 0.061692028507797446,
"max": 0.07478501559433462,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2867403065802315,
"min": 0.24676811403118978,
"max": 0.37392507797167307,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20219715209860428,
"min": 0.11405687301657072,
"max": 0.32349030615067953,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8087886083944171,
"min": 0.4562274920662829,
"max": 1.5221730187243105,
"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": 25.40909090909091,
"min": 3.3863636363636362,
"max": 25.87272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1118.0,
"min": 149.0,
"max": 1423.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.40909090909091,
"min": 3.3863636363636362,
"max": 25.87272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1118.0,
"min": 149.0,
"max": 1423.0,
"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": "1703268635",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1703269100"
},
"total": 465.293668142,
"count": 1,
"self": 0.7066630719998557,
"children": {
"run_training.setup": {
"total": 0.04960173200004192,
"count": 1,
"self": 0.04960173200004192
},
"TrainerController.start_learning": {
"total": 464.5374033380001,
"count": 1,
"self": 0.6271065360155035,
"children": {
"TrainerController._reset_env": {
"total": 3.3911731010000494,
"count": 1,
"self": 3.3911731010000494
},
"TrainerController.advance": {
"total": 460.3868491849847,
"count": 18220,
"self": 0.303753459996301,
"children": {
"env_step": {
"total": 460.0830957249884,
"count": 18220,
"self": 305.63690419598197,
"children": {
"SubprocessEnvManager._take_step": {
"total": 154.14346926000962,
"count": 18220,
"self": 1.5475394530041058,
"children": {
"TorchPolicy.evaluate": {
"total": 152.59592980700552,
"count": 18220,
"self": 152.59592980700552
}
}
},
"workers": {
"total": 0.3027222689968312,
"count": 18220,
"self": 0.0,
"children": {
"worker_root": {
"total": 463.0096428199988,
"count": 18220,
"is_parallel": true,
"self": 225.29393506901397,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005475688999922568,
"count": 1,
"is_parallel": true,
"self": 0.0034161739999944984,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020595149999280693,
"count": 10,
"is_parallel": true,
"self": 0.0020595149999280693
}
}
},
"UnityEnvironment.step": {
"total": 0.04200466999998298,
"count": 1,
"is_parallel": true,
"self": 0.0006533670000408165,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003870499999720778,
"count": 1,
"is_parallel": true,
"self": 0.0003870499999720778
},
"communicator.exchange": {
"total": 0.038961776000064674,
"count": 1,
"is_parallel": true,
"self": 0.038961776000064674
},
"steps_from_proto": {
"total": 0.0020024769999054115,
"count": 1,
"is_parallel": true,
"self": 0.00037318899967431207,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016292880002310994,
"count": 10,
"is_parallel": true,
"self": 0.0016292880002310994
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 237.71570775098485,
"count": 18219,
"is_parallel": true,
"self": 11.093225256010669,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.810693227984643,
"count": 18219,
"is_parallel": true,
"self": 5.810693227984643
},
"communicator.exchange": {
"total": 185.85427779999645,
"count": 18219,
"is_parallel": true,
"self": 185.85427779999645
},
"steps_from_proto": {
"total": 34.95751146699308,
"count": 18219,
"is_parallel": true,
"self": 6.697608579995517,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.259902886997565,
"count": 182190,
"is_parallel": true,
"self": 28.259902886997565
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013265600000522682,
"count": 1,
"self": 0.00013265600000522682,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 454.8035031200494,
"count": 684460,
"is_parallel": true,
"self": 14.142230989072914,
"children": {
"process_trajectory": {
"total": 252.92418852697665,
"count": 684460,
"is_parallel": true,
"self": 251.8398196169768,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0843689099998528,
"count": 4,
"is_parallel": true,
"self": 1.0843689099998528
}
}
},
"_update_policy": {
"total": 187.73708360399985,
"count": 90,
"is_parallel": true,
"self": 57.54304651000439,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.19403709399546,
"count": 4587,
"is_parallel": true,
"self": 130.19403709399546
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13214185999981964,
"count": 1,
"self": 0.0012723379998078599,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13086952200001178,
"count": 1,
"self": 0.13086952200001178
}
}
}
}
}
}
}