EXrRor3's picture
First Push
46409a1
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9362663626670837,
"min": 0.9362663626670837,
"max": 2.871151924133301,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8980.6669921875,
"min": 8980.6669921875,
"max": 29466.6328125,
"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": 12.85880184173584,
"min": 0.3066180646419525,
"max": 12.871854782104492,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2507.46630859375,
"min": 59.48390579223633,
"max": 2622.546875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06499566715249375,
"min": 0.06458037231356026,
"max": 0.07429216690447099,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.259982668609975,
"min": 0.25832148925424103,
"max": 0.37146083452235495,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2080915952283962,
"min": 0.11924259070028534,
"max": 0.2944834412751245,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8323663809135848,
"min": 0.47697036280114136,
"max": 1.4685116679060692,
"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": 25.704545454545453,
"min": 3.340909090909091,
"max": 25.854545454545455,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1131.0,
"min": 147.0,
"max": 1422.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.704545454545453,
"min": 3.340909090909091,
"max": 25.854545454545455,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1131.0,
"min": 147.0,
"max": 1422.0,
"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": "1690602183",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"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": "1690602657"
},
"total": 474.097225523,
"count": 1,
"self": 0.6818936379999059,
"children": {
"run_training.setup": {
"total": 0.061893733000033535,
"count": 1,
"self": 0.061893733000033535
},
"TrainerController.start_learning": {
"total": 473.3534381520001,
"count": 1,
"self": 0.5567151500036971,
"children": {
"TrainerController._reset_env": {
"total": 5.52281425000001,
"count": 1,
"self": 5.52281425000001
},
"TrainerController.advance": {
"total": 467.0413683779965,
"count": 18218,
"self": 0.27270440098345716,
"children": {
"env_step": {
"total": 466.76866397701303,
"count": 18218,
"self": 338.8270470630282,
"children": {
"SubprocessEnvManager._take_step": {
"total": 127.6541236169951,
"count": 18218,
"self": 1.9141821369920535,
"children": {
"TorchPolicy.evaluate": {
"total": 125.73994148000304,
"count": 18218,
"self": 125.73994148000304
}
}
},
"workers": {
"total": 0.28749329698973725,
"count": 18218,
"self": 0.0,
"children": {
"worker_root": {
"total": 471.66126360400585,
"count": 18218,
"is_parallel": true,
"self": 224.13066037501233,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005676341000025786,
"count": 1,
"is_parallel": true,
"self": 0.004153245999759747,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015230950002660393,
"count": 10,
"is_parallel": true,
"self": 0.0015230950002660393
}
}
},
"UnityEnvironment.step": {
"total": 0.03449576600007731,
"count": 1,
"is_parallel": true,
"self": 0.00042727700019895565,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040395899998202367,
"count": 1,
"is_parallel": true,
"self": 0.00040395899998202367
},
"communicator.exchange": {
"total": 0.031795072999898366,
"count": 1,
"is_parallel": true,
"self": 0.031795072999898366
},
"steps_from_proto": {
"total": 0.0018694569999979649,
"count": 1,
"is_parallel": true,
"self": 0.00035213800003930373,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015173189999586612,
"count": 10,
"is_parallel": true,
"self": 0.0015173189999586612
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 247.53060322899353,
"count": 18217,
"is_parallel": true,
"self": 10.700974047979344,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.2730053930202985,
"count": 18217,
"is_parallel": true,
"self": 5.2730053930202985
},
"communicator.exchange": {
"total": 195.99799875000997,
"count": 18217,
"is_parallel": true,
"self": 195.99799875000997
},
"steps_from_proto": {
"total": 35.558625037983916,
"count": 18217,
"is_parallel": true,
"self": 6.540507409999691,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.018117627984225,
"count": 182170,
"is_parallel": true,
"self": 29.018117627984225
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016627199988761276,
"count": 1,
"self": 0.00016627199988761276,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 463.4011751860436,
"count": 435569,
"is_parallel": true,
"self": 9.914446886035876,
"children": {
"process_trajectory": {
"total": 253.76806554600773,
"count": 435569,
"is_parallel": true,
"self": 252.01449039800775,
"children": {
"RLTrainer._checkpoint": {
"total": 1.7535751479999817,
"count": 4,
"is_parallel": true,
"self": 1.7535751479999817
}
}
},
"_update_policy": {
"total": 199.71866275399998,
"count": 90,
"is_parallel": true,
"self": 76.6531684989991,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.06549425500089,
"count": 4584,
"is_parallel": true,
"self": 123.06549425500089
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.2323741019999943,
"count": 1,
"self": 0.0012118879999434284,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23116221400005088,
"count": 1,
"self": 0.23116221400005088
}
}
}
}
}
}
}