Brumocas's picture
Improved Training_1
6f0f7d7 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.601077139377594,
"min": 0.5837947726249695,
"max": 0.9881709814071655,
"count": 80
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 5712.63720703125,
"min": 5643.8955078125,
"max": 10030.509765625,
"count": 80
},
"SnowballTarget.Step.mean": {
"value": 999992.0,
"min": 209936.0,
"max": 999992.0,
"count": 80
},
"SnowballTarget.Step.sum": {
"value": 999992.0,
"min": 209936.0,
"max": 999992.0,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 14.166631698608398,
"min": 12.94360065460205,
"max": 14.166631698608398,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2762.4931640625,
"min": 2485.17138671875,
"max": 2896.8720703125,
"count": 80
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0720234285188638,
"min": 0.060970312462635706,
"max": 0.07712253872637566,
"count": 80
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2880937140754552,
"min": 0.24388124985054283,
"max": 0.369829463961936,
"count": 80
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17329983738269292,
"min": 0.14300536825960758,
"max": 0.23871639186479882,
"count": 80
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6931993495307717,
"min": 0.6001153049223563,
"max": 1.0542938566091014,
"count": 80
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.402899532400004e-06,
"min": 1.402899532400004e-06,
"max": 0.0002383428205524,
"count": 80
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.611598129600016e-06,
"min": 5.611598129600016e-06,
"max": 0.001176864107712,
"count": 80
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1004676,
"min": 0.1004676,
"max": 0.1794476,
"count": 80
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4018704,
"min": 0.4018704,
"max": 0.892288,
"count": 80
},
"SnowballTarget.Policy.Beta.mean": {
"value": 3.3333240000000065e-05,
"min": 3.3333240000000065e-05,
"max": 0.00397443524,
"count": 80
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00013333296000000026,
"min": 0.00013333296000000026,
"max": 0.0196251712,
"count": 80
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 80
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 80
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.545454545454547,
"min": 25.163636363636364,
"max": 27.854545454545455,
"count": 80
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1212.0,
"min": 1116.0,
"max": 1532.0,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.545454545454547,
"min": 25.163636363636364,
"max": 27.854545454545455,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1212.0,
"min": 1116.0,
"max": 1532.0,
"count": 80
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 80
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 80
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1730728012",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1730729744"
},
"total": 1732.12271626,
"count": 1,
"self": 0.5099708959999134,
"children": {
"run_training.setup": {
"total": 0.08511985199993433,
"count": 1,
"self": 0.08511985199993433
},
"TrainerController.start_learning": {
"total": 1731.5276255120002,
"count": 1,
"self": 1.4218081270296352,
"children": {
"TrainerController._reset_env": {
"total": 2.5309698369999296,
"count": 1,
"self": 2.5309698369999296
},
"TrainerController.advance": {
"total": 1727.4860122999705,
"count": 72728,
"self": 1.4741836119442269,
"children": {
"env_step": {
"total": 1224.1766177549985,
"count": 72728,
"self": 931.4992000770171,
"children": {
"SubprocessEnvManager._take_step": {
"total": 291.7915417349475,
"count": 72728,
"self": 5.0668181610044485,
"children": {
"TorchPolicy.evaluate": {
"total": 286.72472357394304,
"count": 72728,
"self": 286.72472357394304
}
}
},
"workers": {
"total": 0.8858759430338523,
"count": 72728,
"self": 0.0,
"children": {
"worker_root": {
"total": 1726.5713134429836,
"count": 72728,
"is_parallel": true,
"self": 910.7163590749676,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002908205000039743,
"count": 1,
"is_parallel": true,
"self": 0.0007877580001149909,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002120446999924752,
"count": 10,
"is_parallel": true,
"self": 0.002120446999924752
}
}
},
"UnityEnvironment.step": {
"total": 0.04131846600012068,
"count": 1,
"is_parallel": true,
"self": 0.0008152610000706773,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003790219998336397,
"count": 1,
"is_parallel": true,
"self": 0.0003790219998336397
},
"communicator.exchange": {
"total": 0.03820512500010409,
"count": 1,
"is_parallel": true,
"self": 0.03820512500010409
},
"steps_from_proto": {
"total": 0.0019190580001122726,
"count": 1,
"is_parallel": true,
"self": 0.00044222899987289566,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001476829000239377,
"count": 10,
"is_parallel": true,
"self": 0.001476829000239377
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 815.854954368016,
"count": 72727,
"is_parallel": true,
"self": 40.134165063941964,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.711173289010503,
"count": 72727,
"is_parallel": true,
"self": 21.711173289010503
},
"communicator.exchange": {
"total": 624.4117628640613,
"count": 72727,
"is_parallel": true,
"self": 624.4117628640613
},
"steps_from_proto": {
"total": 129.59785315100225,
"count": 72727,
"is_parallel": true,
"self": 23.52818316418302,
"children": {
"_process_rank_one_or_two_observation": {
"total": 106.06966998681924,
"count": 727270,
"is_parallel": true,
"self": 106.06966998681924
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 501.83521093302784,
"count": 72728,
"self": 1.719571437992272,
"children": {
"process_trajectory": {
"total": 112.45800108804315,
"count": 72728,
"self": 110.7157728100442,
"children": {
"RLTrainer._checkpoint": {
"total": 1.7422282779989473,
"count": 16,
"self": 1.7422282779989473
}
}
},
"_update_policy": {
"total": 387.6576384069924,
"count": 363,
"self": 159.84262632701825,
"children": {
"TorchPPOOptimizer.update": {
"total": 227.81501207997417,
"count": 18510,
"self": 227.81501207997417
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.680002222012263e-07,
"count": 1,
"self": 9.680002222012263e-07
},
"TrainerController._save_models": {
"total": 0.0888342799999009,
"count": 1,
"self": 0.0011844049995488604,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08764987500035204,
"count": 1,
"self": 0.08764987500035204
}
}
}
}
}
}
}