ML-Matt's picture
First Push
6ecda7c
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0320395231246948,
"min": 1.0320395231246948,
"max": 2.854731559753418,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9876.6181640625,
"min": 9876.6181640625,
"max": 29235.3046875,
"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": 12.72738265991211,
"min": 0.3234580159187317,
"max": 12.72738265991211,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2481.839599609375,
"min": 62.7508544921875,
"max": 2543.093994140625,
"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.Losses.PolicyLoss.mean": {
"value": 0.06422031362650588,
"min": 0.06323554415843069,
"max": 0.07685885090210617,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2568812545060235,
"min": 0.2568812545060235,
"max": 0.3593375044931913,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19836110563254825,
"min": 0.102243716842221,
"max": 0.2590804717120002,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.793444422530193,
"min": 0.408974867368884,
"max": 1.295402358560001,
"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.CumulativeReward.mean": {
"value": 25.204545454545453,
"min": 2.840909090909091,
"max": 25.254545454545454,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1109.0,
"min": 125.0,
"max": 1389.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.204545454545453,
"min": 2.840909090909091,
"max": 25.254545454545454,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1109.0,
"min": 125.0,
"max": 1389.0,
"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": "1702057795",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1702058285"
},
"total": 490.62847872,
"count": 1,
"self": 0.4315736079998942,
"children": {
"run_training.setup": {
"total": 0.06314248099999986,
"count": 1,
"self": 0.06314248099999986
},
"TrainerController.start_learning": {
"total": 490.1337626310001,
"count": 1,
"self": 0.5899538129920074,
"children": {
"TrainerController._reset_env": {
"total": 3.6501364570000305,
"count": 1,
"self": 3.6501364570000305
},
"TrainerController.advance": {
"total": 485.80288327900814,
"count": 18201,
"self": 0.27591633499321233,
"children": {
"env_step": {
"total": 485.52696694401493,
"count": 18201,
"self": 328.41221310200706,
"children": {
"SubprocessEnvManager._take_step": {
"total": 156.8128429340029,
"count": 18201,
"self": 1.5133194070053833,
"children": {
"TorchPolicy.evaluate": {
"total": 155.29952352699752,
"count": 18201,
"self": 155.29952352699752
}
}
},
"workers": {
"total": 0.3019109080049702,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 488.80973424600336,
"count": 18201,
"is_parallel": true,
"self": 241.6034866240061,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005654887999980929,
"count": 1,
"is_parallel": true,
"self": 0.004086547999804679,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015683400001762493,
"count": 10,
"is_parallel": true,
"self": 0.0015683400001762493
}
}
},
"UnityEnvironment.step": {
"total": 0.08423966800000926,
"count": 1,
"is_parallel": true,
"self": 0.0006671279999181934,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044984200008002517,
"count": 1,
"is_parallel": true,
"self": 0.00044984200008002517
},
"communicator.exchange": {
"total": 0.08117492099995616,
"count": 1,
"is_parallel": true,
"self": 0.08117492099995616
},
"steps_from_proto": {
"total": 0.0019477770000548844,
"count": 1,
"is_parallel": true,
"self": 0.00042659200005346065,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015211850000014238,
"count": 10,
"is_parallel": true,
"self": 0.0015211850000014238
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 247.20624762199725,
"count": 18200,
"is_parallel": true,
"self": 10.934555261003425,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.503297810991398,
"count": 18200,
"is_parallel": true,
"self": 5.503297810991398
},
"communicator.exchange": {
"total": 195.6940821250157,
"count": 18200,
"is_parallel": true,
"self": 195.6940821250157
},
"steps_from_proto": {
"total": 35.074312424986715,
"count": 18200,
"is_parallel": true,
"self": 6.621170353004004,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.45314207198271,
"count": 182000,
"is_parallel": true,
"self": 28.45314207198271
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012323200007813284,
"count": 1,
"self": 0.00012323200007813284,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 481.6132735420307,
"count": 506253,
"is_parallel": true,
"self": 11.002084315062234,
"children": {
"process_trajectory": {
"total": 273.11884818096803,
"count": 506253,
"is_parallel": true,
"self": 272.3099773789678,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8088708020002287,
"count": 4,
"is_parallel": true,
"self": 0.8088708020002287
}
}
},
"_update_policy": {
"total": 197.49234104600043,
"count": 90,
"is_parallel": true,
"self": 61.28265647700675,
"children": {
"TorchPPOOptimizer.update": {
"total": 136.20968456899368,
"count": 4587,
"is_parallel": true,
"self": 136.20968456899368
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09066584999982297,
"count": 1,
"self": 0.000985078999747202,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08968077100007577,
"count": 1,
"self": 0.08968077100007577
}
}
}
}
}
}
}