abkimc's picture
First Push
74f20d4 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8509846925735474,
"min": 0.8509846925735474,
"max": 2.8340394496917725,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8087.7587890625,
"min": 8087.7587890625,
"max": 28929.875,
"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": 13.179108619689941,
"min": 0.3355947732925415,
"max": 13.186949729919434,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2569.92626953125,
"min": 65.10538482666016,
"max": 2690.1376953125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0704837701560595,
"min": 0.06236797872058793,
"max": 0.07829990834166072,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.281935080624238,
"min": 0.2545526043264259,
"max": 0.3914995417083036,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20361555243531865,
"min": 0.1297371856270212,
"max": 0.2696867384746963,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8144622097412746,
"min": 0.5189487425080848,
"max": 1.3484336923734817,
"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": 25.636363636363637,
"min": 3.840909090909091,
"max": 26.163636363636364,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1128.0,
"min": 169.0,
"max": 1439.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.636363636363637,
"min": 3.840909090909091,
"max": 26.163636363636364,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1128.0,
"min": 169.0,
"max": 1439.0,
"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": "1751013373",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1751013800"
},
"total": 426.1193176229999,
"count": 1,
"self": 0.43772043399997074,
"children": {
"run_training.setup": {
"total": 0.034447202000023935,
"count": 1,
"self": 0.034447202000023935
},
"TrainerController.start_learning": {
"total": 425.6471499869999,
"count": 1,
"self": 0.345895452996956,
"children": {
"TrainerController._reset_env": {
"total": 3.394971903000055,
"count": 1,
"self": 3.394971903000055
},
"TrainerController.advance": {
"total": 421.8260009920026,
"count": 18192,
"self": 0.3733363580347486,
"children": {
"env_step": {
"total": 299.92921907898904,
"count": 18192,
"self": 229.5440020679988,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.17855775100111,
"count": 18192,
"self": 1.2619964300002948,
"children": {
"TorchPolicy.evaluate": {
"total": 68.91656132100081,
"count": 18192,
"self": 68.91656132100081
}
}
},
"workers": {
"total": 0.2066592599891237,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 424.28339128600555,
"count": 18192,
"is_parallel": true,
"self": 222.63157019601067,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005958706000001257,
"count": 1,
"is_parallel": true,
"self": 0.004545927000094707,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014127789999065499,
"count": 10,
"is_parallel": true,
"self": 0.0014127789999065499
}
}
},
"UnityEnvironment.step": {
"total": 0.036005724999995437,
"count": 1,
"is_parallel": true,
"self": 0.0006072410000115269,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003906040000174471,
"count": 1,
"is_parallel": true,
"self": 0.0003906040000174471
},
"communicator.exchange": {
"total": 0.033195573999933004,
"count": 1,
"is_parallel": true,
"self": 0.033195573999933004
},
"steps_from_proto": {
"total": 0.001812306000033459,
"count": 1,
"is_parallel": true,
"self": 0.0003603919999477512,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014519140000857078,
"count": 10,
"is_parallel": true,
"self": 0.0014519140000857078
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 201.65182108999488,
"count": 18191,
"is_parallel": true,
"self": 9.956840299993928,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.3398060930037445,
"count": 18191,
"is_parallel": true,
"self": 5.3398060930037445
},
"communicator.exchange": {
"total": 155.04007797500674,
"count": 18191,
"is_parallel": true,
"self": 155.04007797500674
},
"steps_from_proto": {
"total": 31.31509672199047,
"count": 18191,
"is_parallel": true,
"self": 5.600647480970338,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.714449241020134,
"count": 181910,
"is_parallel": true,
"self": 25.714449241020134
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.52344555497882,
"count": 18192,
"self": 0.41687439997576803,
"children": {
"process_trajectory": {
"total": 26.363523433002797,
"count": 18192,
"self": 25.913094381002907,
"children": {
"RLTrainer._checkpoint": {
"total": 0.45042905199989036,
"count": 4,
"self": 0.45042905199989036
}
}
},
"_update_policy": {
"total": 94.74304772200026,
"count": 90,
"self": 38.3326668819991,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.41038084000115,
"count": 4587,
"self": 56.41038084000115
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.870001693139784e-07,
"count": 1,
"self": 8.870001693139784e-07
},
"TrainerController._save_models": {
"total": 0.08028075200013518,
"count": 1,
"self": 0.0008165440001448587,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07946420799999032,
"count": 1,
"self": 0.07946420799999032
}
}
}
}
}
}
}