thackerhelik's picture
First training of SnowballTarget
fb27532
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.08695650100708,
"min": 1.08695650100708,
"max": 2.865450143814087,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10402.173828125,
"min": 10402.173828125,
"max": 29313.5546875,
"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": 12.639885902404785,
"min": 0.46872279047966003,
"max": 12.639885902404785,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2464.77783203125,
"min": 90.93222045898438,
"max": 2568.16455078125,
"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": 0.07056197124834665,
"min": 0.06377700367581793,
"max": 0.07541246626822291,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2822478849933866,
"min": 0.2551080147032717,
"max": 0.35796047496157424,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21131635197967874,
"min": 0.12032844984502183,
"max": 0.2885107321482078,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.845265407918715,
"min": 0.48131379938008734,
"max": 1.4425536607410392,
"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": 24.386363636363637,
"min": 3.3863636363636362,
"max": 25.563636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1073.0,
"min": 149.0,
"max": 1406.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.386363636363637,
"min": 3.3863636363636362,
"max": 25.563636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1073.0,
"min": 149.0,
"max": 1406.0,
"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": "1685969680",
"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",
"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": "1685970217"
},
"total": 537.1628565230001,
"count": 1,
"self": 0.44941746000006333,
"children": {
"run_training.setup": {
"total": 0.04405485899997075,
"count": 1,
"self": 0.04405485899997075
},
"TrainerController.start_learning": {
"total": 536.669384204,
"count": 1,
"self": 0.6816082469928233,
"children": {
"TrainerController._reset_env": {
"total": 5.158726107000007,
"count": 1,
"self": 5.158726107000007
},
"TrainerController.advance": {
"total": 530.6812921920074,
"count": 18203,
"self": 0.3170632140274847,
"children": {
"env_step": {
"total": 530.3642289779799,
"count": 18203,
"self": 387.44401485997855,
"children": {
"SubprocessEnvManager._take_step": {
"total": 142.59615606298428,
"count": 18203,
"self": 2.033815088983715,
"children": {
"TorchPolicy.evaluate": {
"total": 140.56234097400056,
"count": 18203,
"self": 140.56234097400056
}
}
},
"workers": {
"total": 0.3240580550170762,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 534.7003151620023,
"count": 18203,
"is_parallel": true,
"self": 248.2258092880047,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006987812000033955,
"count": 1,
"is_parallel": true,
"self": 0.004458171999885963,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0025296400001479924,
"count": 10,
"is_parallel": true,
"self": 0.0025296400001479924
}
}
},
"UnityEnvironment.step": {
"total": 0.08416718499995568,
"count": 1,
"is_parallel": true,
"self": 0.0007284109999545763,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005336330000318412,
"count": 1,
"is_parallel": true,
"self": 0.0005336330000318412
},
"communicator.exchange": {
"total": 0.0742528419999644,
"count": 1,
"is_parallel": true,
"self": 0.0742528419999644
},
"steps_from_proto": {
"total": 0.00865229900000486,
"count": 1,
"is_parallel": true,
"self": 0.00048066699991977657,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.008171632000085083,
"count": 10,
"is_parallel": true,
"self": 0.008171632000085083
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 286.4745058739976,
"count": 18202,
"is_parallel": true,
"self": 11.171711400010736,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.387245966987166,
"count": 18202,
"is_parallel": true,
"self": 6.387245966987166
},
"communicator.exchange": {
"total": 228.1375027399888,
"count": 18202,
"is_parallel": true,
"self": 228.1375027399888
},
"steps_from_proto": {
"total": 40.778045767010894,
"count": 18202,
"is_parallel": true,
"self": 8.241088351043572,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.53695741596732,
"count": 182020,
"is_parallel": true,
"self": 32.53695741596732
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015903099983916036,
"count": 1,
"self": 0.00015903099983916036,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 526.2248538349811,
"count": 516680,
"is_parallel": true,
"self": 12.133222048053995,
"children": {
"process_trajectory": {
"total": 289.6179935619284,
"count": 516680,
"is_parallel": true,
"self": 288.30329859492826,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3146949670001504,
"count": 4,
"is_parallel": true,
"self": 1.3146949670001504
}
}
},
"_update_policy": {
"total": 224.4736382249987,
"count": 90,
"is_parallel": true,
"self": 88.23779648599213,
"children": {
"TorchPPOOptimizer.update": {
"total": 136.23584173900656,
"count": 4587,
"is_parallel": true,
"self": 136.23584173900656
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1475986269999794,
"count": 1,
"self": 0.0008733669999401172,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14672526000003927,
"count": 1,
"self": 0.14672526000003927
}
}
}
}
}
}
}