wlchee's picture
First Push
397d761 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7803475260734558,
"min": 0.7803475260734558,
"max": 2.864386796951294,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7416.4228515625,
"min": 7416.4228515625,
"max": 29239.66015625,
"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": 12.924068450927734,
"min": 0.4250723421573639,
"max": 12.974831581115723,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2520.193359375,
"min": 82.46403503417969,
"max": 2646.86572265625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07395895019270064,
"min": 0.06303286078871358,
"max": 0.076982654971403,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29583580077080257,
"min": 0.2521314431548543,
"max": 0.384913274857015,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20517943806800187,
"min": 0.13167357505938293,
"max": 0.3197867170560594,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8207177522720075,
"min": 0.5266943002375317,
"max": 1.4788143365990882,
"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": 25.704545454545453,
"min": 3.6363636363636362,
"max": 25.954545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1131.0,
"min": 160.0,
"max": 1401.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.704545454545453,
"min": 3.6363636363636362,
"max": 25.954545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1131.0,
"min": 160.0,
"max": 1401.0,
"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": "1742196584",
"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": "1742197028"
},
"total": 444.3496300480001,
"count": 1,
"self": 0.4386175980000644,
"children": {
"run_training.setup": {
"total": 0.030471369999986564,
"count": 1,
"self": 0.030471369999986564
},
"TrainerController.start_learning": {
"total": 443.88054108000006,
"count": 1,
"self": 0.3937901930053158,
"children": {
"TrainerController._reset_env": {
"total": 3.629143618999933,
"count": 1,
"self": 3.629143618999933
},
"TrainerController.advance": {
"total": 439.7687804379948,
"count": 18192,
"self": 0.4079608259971792,
"children": {
"env_step": {
"total": 315.08553834198733,
"count": 18192,
"self": 239.95420343696196,
"children": {
"SubprocessEnvManager._take_step": {
"total": 74.89462998501949,
"count": 18192,
"self": 1.36527331203024,
"children": {
"TorchPolicy.evaluate": {
"total": 73.52935667298925,
"count": 18192,
"self": 73.52935667298925
}
}
},
"workers": {
"total": 0.23670492000587728,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 442.23602936899033,
"count": 18192,
"is_parallel": true,
"self": 231.9864832010128,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.010608316000116247,
"count": 1,
"is_parallel": true,
"self": 0.009129077000579855,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001479238999536392,
"count": 10,
"is_parallel": true,
"self": 0.001479238999536392
}
}
},
"UnityEnvironment.step": {
"total": 0.03878156299992952,
"count": 1,
"is_parallel": true,
"self": 0.0006551449998823955,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003628740000749531,
"count": 1,
"is_parallel": true,
"self": 0.0003628740000749531
},
"communicator.exchange": {
"total": 0.0356077159999586,
"count": 1,
"is_parallel": true,
"self": 0.0356077159999586
},
"steps_from_proto": {
"total": 0.002155828000013571,
"count": 1,
"is_parallel": true,
"self": 0.0004002179996405175,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017556100003730535,
"count": 10,
"is_parallel": true,
"self": 0.0017556100003730535
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 210.24954616797754,
"count": 18191,
"is_parallel": true,
"self": 9.827003821973676,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.575032356000065,
"count": 18191,
"is_parallel": true,
"self": 5.575032356000065
},
"communicator.exchange": {
"total": 161.73969312099848,
"count": 18191,
"is_parallel": true,
"self": 161.73969312099848
},
"steps_from_proto": {
"total": 33.10781686900532,
"count": 18191,
"is_parallel": true,
"self": 6.007568549963935,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.100248319041384,
"count": 181910,
"is_parallel": true,
"self": 27.100248319041384
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 124.27528127001028,
"count": 18192,
"self": 0.5147285820125944,
"children": {
"process_trajectory": {
"total": 27.599224012998775,
"count": 18192,
"self": 27.004680250998717,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5945437620000575,
"count": 4,
"self": 0.5945437620000575
}
}
},
"_update_policy": {
"total": 96.16132867499891,
"count": 90,
"self": 38.74261191700157,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.418716757997345,
"count": 4587,
"self": 57.418716757997345
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.041000132318004e-06,
"count": 1,
"self": 1.041000132318004e-06
},
"TrainerController._save_models": {
"total": 0.08882578899988403,
"count": 1,
"self": 0.0009103540000978683,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08791543499978616,
"count": 1,
"self": 0.08791543499978616
}
}
}
}
}
}
}