AlaaWO's picture
First Push
792ac0e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8970817923545837,
"min": 0.8970817923545837,
"max": 2.8745839595794678,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8565.3369140625,
"min": 8565.3369140625,
"max": 29501.85546875,
"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": 12.286210060119629,
"min": 0.28018951416015625,
"max": 12.286210060119629,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2395.81103515625,
"min": 54.35676574707031,
"max": 2475.2607421875,
"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": 0.07209620044530168,
"min": 0.06364342661616712,
"max": 0.07816516823596412,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28838480178120673,
"min": 0.2586693306885518,
"max": 0.3646259297483815,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18781836831248275,
"min": 0.0917240644978615,
"max": 0.2930439908130496,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.751273473249931,
"min": 0.366896257991446,
"max": 1.465219954065248,
"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": 24.318181818181817,
"min": 2.5681818181818183,
"max": 24.318181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1070.0,
"min": 113.0,
"max": 1322.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.318181818181817,
"min": 2.5681818181818183,
"max": 24.318181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1070.0,
"min": 113.0,
"max": 1322.0,
"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": "1767671805",
"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": "1767672543"
},
"total": 737.258665493,
"count": 1,
"self": 0.5913678949999621,
"children": {
"run_training.setup": {
"total": 0.054690284000002976,
"count": 1,
"self": 0.054690284000002976
},
"TrainerController.start_learning": {
"total": 736.612607314,
"count": 1,
"self": 0.8354003979870868,
"children": {
"TrainerController._reset_env": {
"total": 3.8111426030000075,
"count": 1,
"self": 3.8111426030000075
},
"TrainerController.advance": {
"total": 731.885409823013,
"count": 18201,
"self": 0.4313914650068682,
"children": {
"env_step": {
"total": 731.4540183580061,
"count": 18201,
"self": 601.6184888089966,
"children": {
"SubprocessEnvManager._take_step": {
"total": 129.41679507799574,
"count": 18201,
"self": 2.185412197982373,
"children": {
"TorchPolicy.evaluate": {
"total": 127.23138288001337,
"count": 18201,
"self": 127.23138288001337
}
}
},
"workers": {
"total": 0.4187344710137495,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 732.6874474019992,
"count": 18201,
"is_parallel": true,
"self": 289.0025710309899,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0047652139999172505,
"count": 1,
"is_parallel": true,
"self": 0.0020770360001733934,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002688177999743857,
"count": 10,
"is_parallel": true,
"self": 0.002688177999743857
}
}
},
"UnityEnvironment.step": {
"total": 0.05769984799997019,
"count": 1,
"is_parallel": true,
"self": 0.0007656149998638284,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037675999999464693,
"count": 1,
"is_parallel": true,
"self": 0.00037675999999464693
},
"communicator.exchange": {
"total": 0.05421992800006592,
"count": 1,
"is_parallel": true,
"self": 0.05421992800006592
},
"steps_from_proto": {
"total": 0.002337545000045793,
"count": 1,
"is_parallel": true,
"self": 0.00044246800018754584,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018950769998582473,
"count": 10,
"is_parallel": true,
"self": 0.0018950769998582473
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 443.6848763710093,
"count": 18200,
"is_parallel": true,
"self": 19.50615384302921,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 9.088687439999035,
"count": 18200,
"is_parallel": true,
"self": 9.088687439999035
},
"communicator.exchange": {
"total": 346.8356217320136,
"count": 18200,
"is_parallel": true,
"self": 346.8356217320136
},
"steps_from_proto": {
"total": 68.25441335596747,
"count": 18200,
"is_parallel": true,
"self": 12.492806262922954,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.76160709304452,
"count": 182000,
"is_parallel": true,
"self": 55.76160709304452
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011227400000279886,
"count": 1,
"self": 0.00011227400000279886,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 727.9236483160295,
"count": 418815,
"is_parallel": true,
"self": 10.759198925009287,
"children": {
"process_trajectory": {
"total": 408.3780477330189,
"count": 418815,
"is_parallel": true,
"self": 407.35647908001874,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0215686530001449,
"count": 4,
"is_parallel": true,
"self": 1.0215686530001449
}
}
},
"_update_policy": {
"total": 308.7864016580013,
"count": 90,
"is_parallel": true,
"self": 68.13385406099917,
"children": {
"TorchPPOOptimizer.update": {
"total": 240.65254759700213,
"count": 4587,
"is_parallel": true,
"self": 240.65254759700213
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08054221599991251,
"count": 1,
"self": 0.0009400149999692076,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0796022009999433,
"count": 1,
"self": 0.0796022009999433
}
}
}
}
}
}
}