helpingstar's picture
First Push
cb0d50b
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9247506856918335,
"min": 0.9247506856918335,
"max": 2.8624441623687744,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8860.0361328125,
"min": 8860.0361328125,
"max": 29377.265625,
"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": 12.671814918518066,
"min": 0.376495897769928,
"max": 12.671814918518066,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2471.00390625,
"min": 73.04020690917969,
"max": 2537.899658203125,
"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": 0.07057369544510912,
"min": 0.06226474536480393,
"max": 0.07740275954720166,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2822947817804365,
"min": 0.25513494517140406,
"max": 0.3621523081434562,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20637037261736157,
"min": 0.11181158717612134,
"max": 0.2739654438752754,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8254814904694463,
"min": 0.4472463487044854,
"max": 1.369827219376377,
"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": 24.75,
"min": 3.3636363636363638,
"max": 25.418181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1089.0,
"min": 148.0,
"max": 1398.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.75,
"min": 3.3636363636363638,
"max": 25.418181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1089.0,
"min": 148.0,
"max": 1398.0,
"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": "1679451822",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1679452204"
},
"total": 382.2516619160001,
"count": 1,
"self": 0.32817442300006405,
"children": {
"run_training.setup": {
"total": 0.10802533600008246,
"count": 1,
"self": 0.10802533600008246
},
"TrainerController.start_learning": {
"total": 381.81546215699996,
"count": 1,
"self": 0.48531322098983765,
"children": {
"TrainerController._reset_env": {
"total": 6.0954888559999745,
"count": 1,
"self": 6.0954888559999745
},
"TrainerController.advance": {
"total": 375.10306560301,
"count": 18205,
"self": 0.2530116510295102,
"children": {
"env_step": {
"total": 374.8500539519805,
"count": 18205,
"self": 264.2986406199741,
"children": {
"SubprocessEnvManager._take_step": {
"total": 110.31830584001204,
"count": 18205,
"self": 2.01921268799083,
"children": {
"TorchPolicy.evaluate": {
"total": 108.29909315202121,
"count": 18205,
"self": 108.29909315202121
}
}
},
"workers": {
"total": 0.23310749199436032,
"count": 18205,
"self": 0.0,
"children": {
"worker_root": {
"total": 381.03021259800494,
"count": 18205,
"is_parallel": true,
"self": 193.20011783101017,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018942970000352943,
"count": 1,
"is_parallel": true,
"self": 0.0005747039995185332,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001319593000516761,
"count": 10,
"is_parallel": true,
"self": 0.001319593000516761
}
}
},
"UnityEnvironment.step": {
"total": 0.03373884399979943,
"count": 1,
"is_parallel": true,
"self": 0.0005597449994638737,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038540700006706174,
"count": 1,
"is_parallel": true,
"self": 0.00038540700006706174
},
"communicator.exchange": {
"total": 0.03115190900007292,
"count": 1,
"is_parallel": true,
"self": 0.03115190900007292
},
"steps_from_proto": {
"total": 0.0016417830001955735,
"count": 1,
"is_parallel": true,
"self": 0.0003491529996608733,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012926300005347002,
"count": 10,
"is_parallel": true,
"self": 0.0012926300005347002
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 187.83009476699476,
"count": 18204,
"is_parallel": true,
"self": 8.504639840978825,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.627520658014419,
"count": 18204,
"is_parallel": true,
"self": 4.627520658014419
},
"communicator.exchange": {
"total": 148.17614590200583,
"count": 18204,
"is_parallel": true,
"self": 148.17614590200583
},
"steps_from_proto": {
"total": 26.52178836599569,
"count": 18204,
"is_parallel": true,
"self": 5.08238633808287,
"children": {
"_process_rank_one_or_two_observation": {
"total": 21.43940202791282,
"count": 182040,
"is_parallel": true,
"self": 21.43940202791282
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001430659999641648,
"count": 1,
"self": 0.0001430659999641648,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 373.66136269703657,
"count": 227495,
"is_parallel": true,
"self": 4.817524129085996,
"children": {
"process_trajectory": {
"total": 207.1618734529502,
"count": 227495,
"is_parallel": true,
"self": 206.24940500595062,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9124684469995827,
"count": 4,
"is_parallel": true,
"self": 0.9124684469995827
}
}
},
"_update_policy": {
"total": 161.68196511500037,
"count": 90,
"is_parallel": true,
"self": 41.66495137499601,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.01701374000436,
"count": 4587,
"is_parallel": true,
"self": 120.01701374000436
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.131451411000171,
"count": 1,
"self": 0.000884902000279908,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13056650899989108,
"count": 1,
"self": 0.13056650899989108
}
}
}
}
}
}
}