NeuNav's picture
First Push
a823092 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9739044904708862,
"min": 0.9626721739768982,
"max": 2.871992826461792,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9298.83984375,
"min": 9298.83984375,
"max": 29570.037109375,
"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": 13.157527923583984,
"min": 0.4112570881843567,
"max": 13.157527923583984,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2565.718017578125,
"min": 79.78387451171875,
"max": 2677.76904296875,
"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": 0.07628959746416156,
"min": 0.0603050877509625,
"max": 0.07628959746416156,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.30515838985664623,
"min": 0.24122035100385,
"max": 0.37607987032628015,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20472980400218682,
"min": 0.12417445602306329,
"max": 0.280798314467949,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8189192160087473,
"min": 0.49669782409225316,
"max": 1.3674381559385973,
"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": 25.568181818181817,
"min": 3.6363636363636362,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1125.0,
"min": 160.0,
"max": 1411.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.568181818181817,
"min": 3.6363636363636362,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1125.0,
"min": 160.0,
"max": 1411.0,
"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": "1706796331",
"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": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1706796810"
},
"total": 478.758444026,
"count": 1,
"self": 0.44844799100008004,
"children": {
"run_training.setup": {
"total": 0.05240031599998929,
"count": 1,
"self": 0.05240031599998929
},
"TrainerController.start_learning": {
"total": 478.25759571899994,
"count": 1,
"self": 0.6039348480019271,
"children": {
"TrainerController._reset_env": {
"total": 3.2949044309999636,
"count": 1,
"self": 3.2949044309999636
},
"TrainerController.advance": {
"total": 474.2574071609981,
"count": 18199,
"self": 0.29661162799675367,
"children": {
"env_step": {
"total": 473.9607955330014,
"count": 18199,
"self": 305.8835708339815,
"children": {
"SubprocessEnvManager._take_step": {
"total": 167.75998404301242,
"count": 18199,
"self": 1.5846626360151959,
"children": {
"TorchPolicy.evaluate": {
"total": 166.17532140699723,
"count": 18199,
"self": 166.17532140699723
}
}
},
"workers": {
"total": 0.31724065600747053,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 477.00014416600493,
"count": 18199,
"is_parallel": true,
"self": 236.8382796839984,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0056423570000561085,
"count": 1,
"is_parallel": true,
"self": 0.004077765000033651,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015645920000224578,
"count": 10,
"is_parallel": true,
"self": 0.0015645920000224578
}
}
},
"UnityEnvironment.step": {
"total": 0.04113460999997187,
"count": 1,
"is_parallel": true,
"self": 0.0007703720000336034,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004827139999861174,
"count": 1,
"is_parallel": true,
"self": 0.0004827139999861174
},
"communicator.exchange": {
"total": 0.03639078399999107,
"count": 1,
"is_parallel": true,
"self": 0.03639078399999107
},
"steps_from_proto": {
"total": 0.003490739999961079,
"count": 1,
"is_parallel": true,
"self": 0.0007192860000486689,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00277145399991241,
"count": 10,
"is_parallel": true,
"self": 0.00277145399991241
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 240.16186448200654,
"count": 18198,
"is_parallel": true,
"self": 11.324835772989672,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.900316196999029,
"count": 18198,
"is_parallel": true,
"self": 5.900316196999029
},
"communicator.exchange": {
"total": 185.41560090001076,
"count": 18198,
"is_parallel": true,
"self": 185.41560090001076
},
"steps_from_proto": {
"total": 37.521111612007076,
"count": 18198,
"is_parallel": true,
"self": 7.094128814996225,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.42698279701085,
"count": 181980,
"is_parallel": true,
"self": 30.42698279701085
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012944299999162467,
"count": 1,
"self": 0.00012944299999162467,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 468.1110046619848,
"count": 711067,
"is_parallel": true,
"self": 15.756025684023825,
"children": {
"process_trajectory": {
"total": 256.6933994729609,
"count": 711067,
"is_parallel": true,
"self": 256.1244176719608,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5689818010000636,
"count": 4,
"is_parallel": true,
"self": 0.5689818010000636
}
}
},
"_update_policy": {
"total": 195.66157950500008,
"count": 90,
"is_parallel": true,
"self": 58.618161673000486,
"children": {
"TorchPPOOptimizer.update": {
"total": 137.0434178319996,
"count": 4587,
"is_parallel": true,
"self": 137.0434178319996
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10121983599992745,
"count": 1,
"self": 0.001029223999921669,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10019061200000579,
"count": 1,
"self": 0.10019061200000579
}
}
}
}
}
}
}