{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0600543022155762,
"min": 1.0512789487838745,
"max": 2.869006633758545,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10133.05859375,
"min": 10133.05859375,
"max": 29381.49609375,
"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": 12.738788604736328,
"min": 0.4282965064048767,
"max": 12.738788604736328,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2484.063720703125,
"min": 83.08952331542969,
"max": 2569.8544921875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07062435432731838,
"min": 0.06345376274571297,
"max": 0.073588852267758,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2824974173092735,
"min": 0.25398976699408893,
"max": 0.36794426133879005,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21613895162647845,
"min": 0.13652335082902117,
"max": 0.27511275428182935,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8645558065059138,
"min": 0.5460934033160847,
"max": 1.3755637714091469,
"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": 25.15909090909091,
"min": 3.6363636363636362,
"max": 25.15909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1107.0,
"min": 160.0,
"max": 1375.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.15909090909091,
"min": 3.6363636363636362,
"max": 25.15909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1107.0,
"min": 160.0,
"max": 1375.0,
"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": "1673522147",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1673522599"
},
"total": 451.9925501370001,
"count": 1,
"self": 0.3874491620001663,
"children": {
"run_training.setup": {
"total": 0.11460420399998839,
"count": 1,
"self": 0.11460420399998839
},
"TrainerController.start_learning": {
"total": 451.4904967709999,
"count": 1,
"self": 0.5011956260034367,
"children": {
"TrainerController._reset_env": {
"total": 7.329680439999947,
"count": 1,
"self": 7.329680439999947
},
"TrainerController.advance": {
"total": 443.5389902119964,
"count": 18202,
"self": 0.29623721100142575,
"children": {
"env_step": {
"total": 443.242753000995,
"count": 18202,
"self": 289.1401611989884,
"children": {
"SubprocessEnvManager._take_step": {
"total": 153.82565859600595,
"count": 18202,
"self": 1.4543784579955172,
"children": {
"TorchPolicy.evaluate": {
"total": 152.37128013801043,
"count": 18202,
"self": 34.346135615028516,
"children": {
"TorchPolicy.sample_actions": {
"total": 118.02514452298192,
"count": 18202,
"self": 118.02514452298192
}
}
}
}
},
"workers": {
"total": 0.2769332060006491,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 450.22053515001767,
"count": 18202,
"is_parallel": true,
"self": 219.34455826301496,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00595100900000034,
"count": 1,
"is_parallel": true,
"self": 0.003649169000027541,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002301839999972799,
"count": 10,
"is_parallel": true,
"self": 0.002301839999972799
}
}
},
"UnityEnvironment.step": {
"total": 0.05727657700003874,
"count": 1,
"is_parallel": true,
"self": 0.0028455429999212356,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000290991999918333,
"count": 1,
"is_parallel": true,
"self": 0.000290991999918333
},
"communicator.exchange": {
"total": 0.04963733600015985,
"count": 1,
"is_parallel": true,
"self": 0.04963733600015985
},
"steps_from_proto": {
"total": 0.004502706000039325,
"count": 1,
"is_parallel": true,
"self": 0.0004784320001363085,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004024273999903016,
"count": 10,
"is_parallel": true,
"self": 0.004024273999903016
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 230.8759768870027,
"count": 18201,
"is_parallel": true,
"self": 8.825644798985877,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.455659021994961,
"count": 18201,
"is_parallel": true,
"self": 5.455659021994961
},
"communicator.exchange": {
"total": 183.24953009200863,
"count": 18201,
"is_parallel": true,
"self": 183.24953009200863
},
"steps_from_proto": {
"total": 33.34514297401324,
"count": 18201,
"is_parallel": true,
"self": 7.124796329985429,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.220346644027813,
"count": 182010,
"is_parallel": true,
"self": 26.220346644027813
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.756199996336363e-05,
"count": 1,
"self": 4.756199996336363e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 440.3231474650054,
"count": 352356,
"is_parallel": true,
"self": 9.99236559195424,
"children": {
"process_trajectory": {
"total": 252.06701230805152,
"count": 352356,
"is_parallel": true,
"self": 251.29132779505153,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7756845129999874,
"count": 4,
"is_parallel": true,
"self": 0.7756845129999874
}
}
},
"_update_policy": {
"total": 178.26376956499962,
"count": 90,
"is_parallel": true,
"self": 44.519399499993824,
"children": {
"TorchPPOOptimizer.update": {
"total": 133.7443700650058,
"count": 4587,
"is_parallel": true,
"self": 133.7443700650058
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12058293100017181,
"count": 1,
"self": 0.0008141050002450356,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11976882599992678,
"count": 1,
"self": 0.11976882599992678
}
}
}
}
}
}
}