Sakura5201's picture
First Push
56edfa5 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6032175421714783,
"min": 0.6032175421714783,
"max": 2.852449893951416,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 5732.9794921875,
"min": 5732.9794921875,
"max": 29117.80859375,
"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": 12.921707153320312,
"min": 0.3979354798793793,
"max": 12.921707153320312,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2519.73291015625,
"min": 77.1994857788086,
"max": 2619.0615234375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0725490986804681,
"min": 0.06143364131172597,
"max": 0.07945754026364096,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2901963947218724,
"min": 0.24573456524690387,
"max": 0.3972877013182048,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18861383469957932,
"min": 0.12866523634076266,
"max": 0.27707328983381685,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7544553387983173,
"min": 0.5146609453630506,
"max": 1.3535084949404586,
"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": 25.295454545454547,
"min": 3.5454545454545454,
"max": 25.527272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1113.0,
"min": 156.0,
"max": 1404.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.295454545454547,
"min": 3.5454545454545454,
"max": 25.527272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1113.0,
"min": 156.0,
"max": 1404.0,
"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": "1743227501",
"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": "1743227940"
},
"total": 438.72499507299995,
"count": 1,
"self": 0.4384621070001913,
"children": {
"run_training.setup": {
"total": 0.022586969999906614,
"count": 1,
"self": 0.022586969999906614
},
"TrainerController.start_learning": {
"total": 438.26394599599985,
"count": 1,
"self": 0.356374899010234,
"children": {
"TrainerController._reset_env": {
"total": 2.8957989760000373,
"count": 1,
"self": 2.8957989760000373
},
"TrainerController.advance": {
"total": 434.91902311998945,
"count": 18192,
"self": 0.3786250249737577,
"children": {
"env_step": {
"total": 310.9350831300105,
"count": 18192,
"self": 236.53104704601458,
"children": {
"SubprocessEnvManager._take_step": {
"total": 74.18044929299788,
"count": 18192,
"self": 1.2922308799956,
"children": {
"TorchPolicy.evaluate": {
"total": 72.88821841300228,
"count": 18192,
"self": 72.88821841300228
}
}
},
"workers": {
"total": 0.22358679099806977,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 436.86410527400506,
"count": 18192,
"is_parallel": true,
"self": 229.2196483190104,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007675065000057657,
"count": 1,
"is_parallel": true,
"self": 0.005363161999866861,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002311903000190796,
"count": 10,
"is_parallel": true,
"self": 0.002311903000190796
}
}
},
"UnityEnvironment.step": {
"total": 0.03829297300001144,
"count": 1,
"is_parallel": true,
"self": 0.0006029320001061933,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003757629999654455,
"count": 1,
"is_parallel": true,
"self": 0.0003757629999654455
},
"communicator.exchange": {
"total": 0.035335778999979084,
"count": 1,
"is_parallel": true,
"self": 0.035335778999979084
},
"steps_from_proto": {
"total": 0.0019784989999607205,
"count": 1,
"is_parallel": true,
"self": 0.00042217299994717905,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015563260000135415,
"count": 10,
"is_parallel": true,
"self": 0.0015563260000135415
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 207.64445695499467,
"count": 18191,
"is_parallel": true,
"self": 9.927232289991139,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.609671692999541,
"count": 18191,
"is_parallel": true,
"self": 5.609671692999541
},
"communicator.exchange": {
"total": 159.15462182700162,
"count": 18191,
"is_parallel": true,
"self": 159.15462182700162
},
"steps_from_proto": {
"total": 32.95293114500237,
"count": 18191,
"is_parallel": true,
"self": 5.936507339009609,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.01642380599276,
"count": 181910,
"is_parallel": true,
"self": 27.01642380599276
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 123.60531496500516,
"count": 18192,
"self": 0.46386276800456017,
"children": {
"process_trajectory": {
"total": 27.709405817000288,
"count": 18192,
"self": 27.192832811000244,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5165730060000442,
"count": 4,
"self": 0.5165730060000442
}
}
},
"_update_policy": {
"total": 95.43204638000032,
"count": 90,
"self": 38.05562597600215,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.37642040399817,
"count": 4587,
"self": 57.37642040399817
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4890001693856902e-06,
"count": 1,
"self": 1.4890001693856902e-06
},
"TrainerController._save_models": {
"total": 0.0927475119999599,
"count": 1,
"self": 0.0009380219999002293,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09180949000005967,
"count": 1,
"self": 0.09180949000005967
}
}
}
}
}
}
}