ranranrunforit's picture
First Push
c14c85e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7823391556739807,
"min": 0.7823391556739807,
"max": 2.865589141845703,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7435.35107421875,
"min": 7435.35107421875,
"max": 29251.93359375,
"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": 12.876214027404785,
"min": 0.4383032023906708,
"max": 12.90781021118164,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2510.86181640625,
"min": 85.03082275390625,
"max": 2643.940185546875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06584483530619478,
"min": 0.05789498571664844,
"max": 0.07444966168045941,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26337934122477913,
"min": 0.25727131010909726,
"max": 0.35112881186867917,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18582262726975424,
"min": 0.1337264442597242,
"max": 0.29020314695788363,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.743290509079017,
"min": 0.5349057770388967,
"max": 1.4510157347894181,
"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": 25.136363636363637,
"min": 4.090909090909091,
"max": 25.78181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1106.0,
"min": 180.0,
"max": 1418.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.136363636363637,
"min": 4.090909090909091,
"max": 25.78181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1106.0,
"min": 180.0,
"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": "1745817054",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1745817506"
},
"total": 452.13088790899997,
"count": 1,
"self": 0.536782141000117,
"children": {
"run_training.setup": {
"total": 0.024612127999944278,
"count": 1,
"self": 0.024612127999944278
},
"TrainerController.start_learning": {
"total": 451.5694936399999,
"count": 1,
"self": 0.3657225460032123,
"children": {
"TrainerController._reset_env": {
"total": 3.2360039709999455,
"count": 1,
"self": 3.2360039709999455
},
"TrainerController.advance": {
"total": 447.8721128299967,
"count": 18192,
"self": 0.4108934939841902,
"children": {
"env_step": {
"total": 320.2663241570061,
"count": 18192,
"self": 243.66551716200797,
"children": {
"SubprocessEnvManager._take_step": {
"total": 76.3832638259945,
"count": 18192,
"self": 1.3390278459869478,
"children": {
"TorchPolicy.evaluate": {
"total": 75.04423598000756,
"count": 18192,
"self": 75.04423598000756
}
}
},
"workers": {
"total": 0.21754316900364756,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 450.0215885900069,
"count": 18192,
"is_parallel": true,
"self": 236.59638757001414,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004734003000066878,
"count": 1,
"is_parallel": true,
"self": 0.003165268000316246,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015687349997506317,
"count": 10,
"is_parallel": true,
"self": 0.0015687349997506317
}
}
},
"UnityEnvironment.step": {
"total": 0.06956742200009103,
"count": 1,
"is_parallel": true,
"self": 0.0006504729999505798,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003861720000486457,
"count": 1,
"is_parallel": true,
"self": 0.0003861720000486457
},
"communicator.exchange": {
"total": 0.05893795000008595,
"count": 1,
"is_parallel": true,
"self": 0.05893795000008595
},
"steps_from_proto": {
"total": 0.009592827000005855,
"count": 1,
"is_parallel": true,
"self": 0.00044370599982812564,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.009149121000177729,
"count": 10,
"is_parallel": true,
"self": 0.009149121000177729
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 213.42520101999276,
"count": 18191,
"is_parallel": true,
"self": 10.271829192007203,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.746890288986378,
"count": 18191,
"is_parallel": true,
"self": 5.746890288986378
},
"communicator.exchange": {
"total": 163.76960242900236,
"count": 18191,
"is_parallel": true,
"self": 163.76960242900236
},
"steps_from_proto": {
"total": 33.63687910999681,
"count": 18191,
"is_parallel": true,
"self": 6.143428745994925,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.493450364001887,
"count": 181910,
"is_parallel": true,
"self": 27.493450364001887
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 127.19489517900638,
"count": 18192,
"self": 0.45219731798988505,
"children": {
"process_trajectory": {
"total": 28.265662891016973,
"count": 18192,
"self": 27.807201386016914,
"children": {
"RLTrainer._checkpoint": {
"total": 0.45846150500005933,
"count": 4,
"self": 0.45846150500005933
}
}
},
"_update_policy": {
"total": 98.47703496999952,
"count": 90,
"self": 40.680915456002936,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.79611951399659,
"count": 4587,
"self": 57.79611951399659
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0219999921901035e-06,
"count": 1,
"self": 1.0219999921901035e-06
},
"TrainerController._save_models": {
"total": 0.09565327100006016,
"count": 1,
"self": 0.0009355160001405238,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09471775499991963,
"count": 1,
"self": 0.09471775499991963
}
}
}
}
}
}
}