Balab2021's picture
First Push
3aece8a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9734007716178894,
"min": 0.9734007716178894,
"max": 2.840930938720703,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9251.201171875,
"min": 9251.201171875,
"max": 29000.22265625,
"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": 13.17613697052002,
"min": 0.4330487549304962,
"max": 13.17613697052002,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2569.3466796875,
"min": 84.01145935058594,
"max": 2668.453125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07505593754945485,
"min": 0.06181131327182847,
"max": 0.0768056135184095,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3002237501978194,
"min": 0.24724525308731388,
"max": 0.3774971572223448,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21283396779029978,
"min": 0.13966708885067525,
"max": 0.3056896312564027,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8513358711611991,
"min": 0.558668355402701,
"max": 1.5284481562820136,
"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": 25.431818181818183,
"min": 4.386363636363637,
"max": 25.78181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1119.0,
"min": 193.0,
"max": 1418.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.431818181818183,
"min": 4.386363636363637,
"max": 25.78181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1119.0,
"min": 193.0,
"max": 1418.0,
"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": "1738695991",
"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": "1738696575"
},
"total": 584.37370413,
"count": 1,
"self": 0.5375780050000003,
"children": {
"run_training.setup": {
"total": 0.034259703999964586,
"count": 1,
"self": 0.034259703999964586
},
"TrainerController.start_learning": {
"total": 583.801866421,
"count": 1,
"self": 0.6244589130036502,
"children": {
"TrainerController._reset_env": {
"total": 3.83298597299995,
"count": 1,
"self": 3.83298597299995
},
"TrainerController.advance": {
"total": 579.2568668949962,
"count": 18192,
"self": 0.6379939019873291,
"children": {
"env_step": {
"total": 401.8304817430088,
"count": 18192,
"self": 340.992025279009,
"children": {
"SubprocessEnvManager._take_step": {
"total": 60.464567351998994,
"count": 18192,
"self": 2.2110836829936034,
"children": {
"TorchPolicy.evaluate": {
"total": 58.25348366900539,
"count": 18192,
"self": 58.25348366900539
}
}
},
"workers": {
"total": 0.37388911200082475,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 581.6121238170072,
"count": 18192,
"is_parallel": true,
"self": 287.4441795400029,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007298810000065714,
"count": 1,
"is_parallel": true,
"self": 0.004943506000131492,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002355303999934222,
"count": 10,
"is_parallel": true,
"self": 0.002355303999934222
}
}
},
"UnityEnvironment.step": {
"total": 0.0466708709999466,
"count": 1,
"is_parallel": true,
"self": 0.0009063349998541526,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043911400007345947,
"count": 1,
"is_parallel": true,
"self": 0.00043911400007345947
},
"communicator.exchange": {
"total": 0.042967144000044755,
"count": 1,
"is_parallel": true,
"self": 0.042967144000044755
},
"steps_from_proto": {
"total": 0.0023582779999742343,
"count": 1,
"is_parallel": true,
"self": 0.00044907300002705597,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019092049999471783,
"count": 10,
"is_parallel": true,
"self": 0.0019092049999471783
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 294.16794427700427,
"count": 18191,
"is_parallel": true,
"self": 13.56301541300229,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.549516758011805,
"count": 18191,
"is_parallel": true,
"self": 7.549516758011805
},
"communicator.exchange": {
"total": 231.68514345299673,
"count": 18191,
"is_parallel": true,
"self": 231.68514345299673
},
"steps_from_proto": {
"total": 41.370268652993445,
"count": 18191,
"is_parallel": true,
"self": 8.110472834992265,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.25979581800118,
"count": 181910,
"is_parallel": true,
"self": 33.25979581800118
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 176.78839125000002,
"count": 18192,
"self": 0.7981750700071188,
"children": {
"process_trajectory": {
"total": 32.92713713399189,
"count": 18192,
"self": 32.36163306799142,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5655040660004715,
"count": 4,
"self": 0.5655040660004715
}
}
},
"_update_policy": {
"total": 143.063079046001,
"count": 90,
"self": 52.004258849997655,
"children": {
"TorchPPOOptimizer.update": {
"total": 91.05882019600335,
"count": 4587,
"self": 91.05882019600335
}
}
}
}
}
}
},
"trainer_threads": {
"total": 2.0360000689834123e-06,
"count": 1,
"self": 2.0360000689834123e-06
},
"TrainerController._save_models": {
"total": 0.08755260400016596,
"count": 1,
"self": 0.0011940210001739615,
"children": {
"RLTrainer._checkpoint": {
"total": 0.086358582999992,
"count": 1,
"self": 0.086358582999992
}
}
}
}
}
}
}