Yuseifer's picture
First Push
45f1602 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9385861158370972,
"min": 0.9385861158370972,
"max": 2.8513100147247314,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8951.2958984375,
"min": 8951.2958984375,
"max": 29200.265625,
"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": 12.821311950683594,
"min": 0.21420244872570038,
"max": 12.821311950683594,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2500.15576171875,
"min": 41.555274963378906,
"max": 2598.53955078125,
"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": 0.058902991483288744,
"min": 0.058902991483288744,
"max": 0.07282058774424015,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.23561196593315498,
"min": 0.23561196593315498,
"max": 0.34833562168333787,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21540895111712755,
"min": 0.10660024658507466,
"max": 0.28086931734692816,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8616358044685102,
"min": 0.42640098634029866,
"max": 1.4043465867346407,
"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": 25.295454545454547,
"min": 2.9545454545454546,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1113.0,
"min": 130.0,
"max": 1378.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.295454545454547,
"min": 2.9545454545454546,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1113.0,
"min": 130.0,
"max": 1378.0,
"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": "1719174775",
"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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1719175261"
},
"total": 485.10374857000005,
"count": 1,
"self": 0.4365811520000875,
"children": {
"run_training.setup": {
"total": 0.05620843200000536,
"count": 1,
"self": 0.05620843200000536
},
"TrainerController.start_learning": {
"total": 484.61095898599996,
"count": 1,
"self": 0.6321470470081181,
"children": {
"TrainerController._reset_env": {
"total": 2.8815836260000083,
"count": 1,
"self": 2.8815836260000083
},
"TrainerController.advance": {
"total": 481.0010278889917,
"count": 18201,
"self": 0.31197661799160414,
"children": {
"env_step": {
"total": 480.6890512710001,
"count": 18201,
"self": 315.1310754709783,
"children": {
"SubprocessEnvManager._take_step": {
"total": 165.2459657300099,
"count": 18201,
"self": 1.5736958320101166,
"children": {
"TorchPolicy.evaluate": {
"total": 163.6722698979998,
"count": 18201,
"self": 163.6722698979998
}
}
},
"workers": {
"total": 0.31201007001186554,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 483.31323522799926,
"count": 18201,
"is_parallel": true,
"self": 241.7507801849938,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004771475000040937,
"count": 1,
"is_parallel": true,
"self": 0.003201668999906815,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015698060001341219,
"count": 10,
"is_parallel": true,
"self": 0.0015698060001341219
}
}
},
"UnityEnvironment.step": {
"total": 0.07234664999998586,
"count": 1,
"is_parallel": true,
"self": 0.0006941450000113036,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038742300000649266,
"count": 1,
"is_parallel": true,
"self": 0.00038742300000649266
},
"communicator.exchange": {
"total": 0.06917882999999847,
"count": 1,
"is_parallel": true,
"self": 0.06917882999999847
},
"steps_from_proto": {
"total": 0.0020862519999695905,
"count": 1,
"is_parallel": true,
"self": 0.0005061019999743621,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015801499999952284,
"count": 10,
"is_parallel": true,
"self": 0.0015801499999952284
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 241.56245504300546,
"count": 18200,
"is_parallel": true,
"self": 10.761935405000202,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.774247303005552,
"count": 18200,
"is_parallel": true,
"self": 5.774247303005552
},
"communicator.exchange": {
"total": 189.014387728001,
"count": 18200,
"is_parallel": true,
"self": 189.014387728001
},
"steps_from_proto": {
"total": 36.011884606998706,
"count": 18200,
"is_parallel": true,
"self": 7.022180013008608,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.989704593990098,
"count": 182000,
"is_parallel": true,
"self": 28.989704593990098
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00021636300004956865,
"count": 1,
"self": 0.00021636300004956865,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 475.0911060749384,
"count": 717156,
"is_parallel": true,
"self": 15.28952739792743,
"children": {
"process_trajectory": {
"total": 265.0537030600103,
"count": 717156,
"is_parallel": true,
"self": 264.31331262301023,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7403904370000873,
"count": 4,
"is_parallel": true,
"self": 0.7403904370000873
}
}
},
"_update_policy": {
"total": 194.74787561700066,
"count": 90,
"is_parallel": true,
"self": 58.98256387800296,
"children": {
"TorchPPOOptimizer.update": {
"total": 135.7653117389977,
"count": 4587,
"is_parallel": true,
"self": 135.7653117389977
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09598406100008106,
"count": 1,
"self": 0.0009985000001506705,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09498556099993039,
"count": 1,
"self": 0.09498556099993039
}
}
}
}
}
}
}