ale2x72's picture
First Push
7c19233 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0569707155227661,
"min": 1.0569707155227661,
"max": 2.8467185497283936,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10045.4501953125,
"min": 10045.4501953125,
"max": 29059.302734375,
"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": 12.100786209106445,
"min": 0.48602059483528137,
"max": 12.100786209106445,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2359.6533203125,
"min": 94.28799438476562,
"max": 2457.669189453125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07574302609696043,
"min": 0.060599374820394944,
"max": 0.07574302609696043,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3029721043878417,
"min": 0.24239749928157978,
"max": 0.3501970388289705,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18658530814390556,
"min": 0.12448306868478254,
"max": 0.28834193287526866,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7463412325756222,
"min": 0.49793227473913015,
"max": 1.4188936875731337,
"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.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.Environment.CumulativeReward.mean": {
"value": 23.772727272727273,
"min": 3.840909090909091,
"max": 23.772727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1046.0,
"min": 169.0,
"max": 1298.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.772727272727273,
"min": 3.840909090909091,
"max": 23.772727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1046.0,
"min": 169.0,
"max": 1298.0,
"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": "1770808113",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1770808555"
},
"total": 442.03352837399996,
"count": 1,
"self": 0.43938317099980395,
"children": {
"run_training.setup": {
"total": 0.025637476000042625,
"count": 1,
"self": 0.025637476000042625
},
"TrainerController.start_learning": {
"total": 441.5685077270001,
"count": 1,
"self": 0.34365901499643314,
"children": {
"TrainerController._reset_env": {
"total": 2.708376520999991,
"count": 1,
"self": 2.708376520999991
},
"TrainerController.advance": {
"total": 438.42918197200356,
"count": 18192,
"self": 0.3741712080253592,
"children": {
"env_step": {
"total": 319.40368606898846,
"count": 18192,
"self": 249.14820656598658,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.0520620910039,
"count": 18192,
"self": 1.2341644499914537,
"children": {
"TorchPolicy.evaluate": {
"total": 68.81789764101245,
"count": 18192,
"self": 68.81789764101245
}
}
},
"workers": {
"total": 0.20341741199797525,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 439.8683194830003,
"count": 18192,
"is_parallel": true,
"self": 220.73624114499682,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004352336000010837,
"count": 1,
"is_parallel": true,
"self": 0.0029896699999198972,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013626660000909396,
"count": 10,
"is_parallel": true,
"self": 0.0013626660000909396
}
}
},
"UnityEnvironment.step": {
"total": 0.03545432600003551,
"count": 1,
"is_parallel": true,
"self": 0.0006516130000591147,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041537300000982214,
"count": 1,
"is_parallel": true,
"self": 0.00041537300000982214
},
"communicator.exchange": {
"total": 0.03261318699992444,
"count": 1,
"is_parallel": true,
"self": 0.03261318699992444
},
"steps_from_proto": {
"total": 0.0017741530000421335,
"count": 1,
"is_parallel": true,
"self": 0.0003465290003532573,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014276239996888762,
"count": 10,
"is_parallel": true,
"self": 0.0014276239996888762
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 219.13207833800345,
"count": 18191,
"is_parallel": true,
"self": 10.503781831992342,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.586042768003381,
"count": 18191,
"is_parallel": true,
"self": 5.586042768003381
},
"communicator.exchange": {
"total": 166.32122117600863,
"count": 18191,
"is_parallel": true,
"self": 166.32122117600863
},
"steps_from_proto": {
"total": 36.721032561999095,
"count": 18191,
"is_parallel": true,
"self": 6.529597719961657,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.191434842037438,
"count": 181910,
"is_parallel": true,
"self": 30.191434842037438
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 118.65132469498974,
"count": 18192,
"self": 0.4272253349984112,
"children": {
"process_trajectory": {
"total": 26.379392059991687,
"count": 18192,
"self": 25.860673016991427,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5187190430002602,
"count": 4,
"self": 0.5187190430002602
}
}
},
"_update_policy": {
"total": 91.84470729999964,
"count": 90,
"self": 36.87490439299961,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.96980290700003,
"count": 4587,
"self": 54.96980290700003
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0730000212788582e-06,
"count": 1,
"self": 1.0730000212788582e-06
},
"TrainerController._save_models": {
"total": 0.08728914600010285,
"count": 1,
"self": 0.0007412290001411748,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08654791699996167,
"count": 1,
"self": 0.08654791699996167
}
}
}
}
}
}
}