Zarzd's picture
First Push
d4eaeba verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9040477275848389,
"min": 0.8962529301643372,
"max": 2.827312469482422,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8592.0693359375,
"min": 8592.0693359375,
"max": 28861.205078125,
"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": 13.139816284179688,
"min": 0.50865638256073,
"max": 13.139816284179688,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2562.26416015625,
"min": 98.67933654785156,
"max": 2664.583984375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07414273246211131,
"min": 0.062398120407334653,
"max": 0.07414273246211131,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29657092984844524,
"min": 0.2507316188362964,
"max": 0.3654929886334667,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22314459472602488,
"min": 0.12376687080512627,
"max": 0.2592683199573965,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8925783789040995,
"min": 0.4950674832205051,
"max": 1.2963415997869827,
"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": 25.181818181818183,
"min": 3.6136363636363638,
"max": 25.98181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1108.0,
"min": 159.0,
"max": 1429.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.181818181818183,
"min": 3.6136363636363638,
"max": 25.98181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1108.0,
"min": 159.0,
"max": 1429.0,
"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": "1738666757",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1738667319"
},
"total": 561.1677821950001,
"count": 1,
"self": 0.6432646079999813,
"children": {
"run_training.setup": {
"total": 0.02805434200001855,
"count": 1,
"self": 0.02805434200001855
},
"TrainerController.start_learning": {
"total": 560.4964632450001,
"count": 1,
"self": 0.5996205809938147,
"children": {
"TrainerController._reset_env": {
"total": 3.20850886300002,
"count": 1,
"self": 3.20850886300002
},
"TrainerController.advance": {
"total": 556.6024974230062,
"count": 18192,
"self": 0.6433410800124193,
"children": {
"env_step": {
"total": 390.8664945999973,
"count": 18192,
"self": 332.9466219469924,
"children": {
"SubprocessEnvManager._take_step": {
"total": 57.55122882000353,
"count": 18192,
"self": 2.041202998009112,
"children": {
"TorchPolicy.evaluate": {
"total": 55.51002582199442,
"count": 18192,
"self": 55.51002582199442
}
}
},
"workers": {
"total": 0.36864383300132886,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 558.2978829409897,
"count": 18192,
"is_parallel": true,
"self": 272.0845039120003,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006195843999989847,
"count": 1,
"is_parallel": true,
"self": 0.004392018999737957,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018038250002518907,
"count": 10,
"is_parallel": true,
"self": 0.0018038250002518907
}
}
},
"UnityEnvironment.step": {
"total": 0.04165938400001323,
"count": 1,
"is_parallel": true,
"self": 0.0007430849998399935,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004842730000973461,
"count": 1,
"is_parallel": true,
"self": 0.0004842730000973461
},
"communicator.exchange": {
"total": 0.03823218900004122,
"count": 1,
"is_parallel": true,
"self": 0.03823218900004122
},
"steps_from_proto": {
"total": 0.0021998370000346767,
"count": 1,
"is_parallel": true,
"self": 0.00042757500011703087,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017722619999176459,
"count": 10,
"is_parallel": true,
"self": 0.0017722619999176459
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 286.2133790289894,
"count": 18191,
"is_parallel": true,
"self": 13.907698725017099,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.585535001991161,
"count": 18191,
"is_parallel": true,
"self": 7.585535001991161
},
"communicator.exchange": {
"total": 223.63463154799217,
"count": 18191,
"is_parallel": true,
"self": 223.63463154799217
},
"steps_from_proto": {
"total": 41.08551375398895,
"count": 18191,
"is_parallel": true,
"self": 7.976800990028664,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.108712763960284,
"count": 181910,
"is_parallel": true,
"self": 33.108712763960284
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 165.09266174299648,
"count": 18192,
"self": 0.8381261599921572,
"children": {
"process_trajectory": {
"total": 31.951846547004834,
"count": 18192,
"self": 31.439854496004955,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5119920509998792,
"count": 4,
"self": 0.5119920509998792
}
}
},
"_update_policy": {
"total": 132.3026890359995,
"count": 90,
"self": 50.975816055002156,
"children": {
"TorchPPOOptimizer.update": {
"total": 81.32687298099734,
"count": 4587,
"self": 81.32687298099734
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2130001323384931e-06,
"count": 1,
"self": 1.2130001323384931e-06
},
"TrainerController._save_models": {
"total": 0.08583516499993493,
"count": 1,
"self": 0.0012560839998059237,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08457908100012901,
"count": 1,
"self": 0.08457908100012901
}
}
}
}
}
}
}