hugginglaoda's picture
First Push
cdea16a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9443433284759521,
"min": 0.9443433284759521,
"max": 2.840646982192993,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8975.0390625,
"min": 8975.0390625,
"max": 28997.32421875,
"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": 11.830558776855469,
"min": 0.2839992046356201,
"max": 11.830558776855469,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2306.958984375,
"min": 55.09584426879883,
"max": 2382.488037109375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06985937957863059,
"min": 0.06451399922005686,
"max": 0.0737943585118046,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27943751831452235,
"min": 0.25805599688022746,
"max": 0.3461206583454566,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20863206816070218,
"min": 0.13478914894821015,
"max": 0.27229715597395804,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8345282726428087,
"min": 0.5391565957928406,
"max": 1.3614857798697901,
"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": 23.5,
"min": 3.3181818181818183,
"max": 23.5,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1034.0,
"min": 146.0,
"max": 1255.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.5,
"min": 3.3181818181818183,
"max": 23.5,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1034.0,
"min": 146.0,
"max": 1255.0,
"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": "1742543694",
"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": "1742544117"
},
"total": 423.2979905909999,
"count": 1,
"self": 0.44001001799983896,
"children": {
"run_training.setup": {
"total": 0.031857629000114684,
"count": 1,
"self": 0.031857629000114684
},
"TrainerController.start_learning": {
"total": 422.82612294399996,
"count": 1,
"self": 0.3330960140106072,
"children": {
"TrainerController._reset_env": {
"total": 3.2697990829999526,
"count": 1,
"self": 3.2697990829999526
},
"TrainerController.advance": {
"total": 419.1366047869899,
"count": 18192,
"self": 0.3494798529889067,
"children": {
"env_step": {
"total": 297.64177182400203,
"count": 18192,
"self": 226.72756490796155,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.70356293002965,
"count": 18192,
"self": 1.247727862025613,
"children": {
"TorchPolicy.evaluate": {
"total": 69.45583506800403,
"count": 18192,
"self": 69.45583506800403
}
}
},
"workers": {
"total": 0.21064398601083667,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 421.37535863798644,
"count": 18192,
"is_parallel": true,
"self": 222.071455871971,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.01134388100012984,
"count": 1,
"is_parallel": true,
"self": 0.009858641000164425,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014852399999654153,
"count": 10,
"is_parallel": true,
"self": 0.0014852399999654153
}
}
},
"UnityEnvironment.step": {
"total": 0.03487937299996702,
"count": 1,
"is_parallel": true,
"self": 0.0005835249999108783,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004089960000328574,
"count": 1,
"is_parallel": true,
"self": 0.0004089960000328574
},
"communicator.exchange": {
"total": 0.03192005599998993,
"count": 1,
"is_parallel": true,
"self": 0.03192005599998993
},
"steps_from_proto": {
"total": 0.001966796000033355,
"count": 1,
"is_parallel": true,
"self": 0.00036942299993825145,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015973730000951036,
"count": 10,
"is_parallel": true,
"self": 0.0015973730000951036
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 199.30390276601543,
"count": 18191,
"is_parallel": true,
"self": 9.649495478016206,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.396380068971212,
"count": 18191,
"is_parallel": true,
"self": 5.396380068971212
},
"communicator.exchange": {
"total": 152.60529898401523,
"count": 18191,
"is_parallel": true,
"self": 152.60529898401523
},
"steps_from_proto": {
"total": 31.652728235012773,
"count": 18191,
"is_parallel": true,
"self": 5.6929848818890605,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.959743353123713,
"count": 181910,
"is_parallel": true,
"self": 25.959743353123713
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.14535310999895,
"count": 18192,
"self": 0.4286687519672796,
"children": {
"process_trajectory": {
"total": 26.89346503903016,
"count": 18192,
"self": 26.359924842030296,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5335401969998657,
"count": 4,
"self": 0.5335401969998657
}
}
},
"_update_policy": {
"total": 93.82321931900151,
"count": 90,
"self": 38.369049520996896,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.454169798004614,
"count": 4587,
"self": 55.454169798004614
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.319996934209485e-07,
"count": 1,
"self": 9.319996934209485e-07
},
"TrainerController._save_models": {
"total": 0.08662212799981717,
"count": 1,
"self": 0.0008751999998821702,
"children": {
"RLTrainer._checkpoint": {
"total": 0.085746927999935,
"count": 1,
"self": 0.085746927999935
}
}
}
}
}
}
}