itsdhanoob's picture
First Push
c7b060c verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6252679824829102,
"min": 0.624529242515564,
"max": 2.870626926422119,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 5997.5703125,
"min": 5989.09765625,
"max": 29303.359375,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.67173957824707,
"min": 0.42167872190475464,
"max": 13.67173957824707,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2802.70654296875,
"min": 81.80567169189453,
"max": 2802.70654296875,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.05052012774103787,
"min": 0.038355798037779706,
"max": 0.05712074281372755,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25260063870518934,
"min": 0.15342319215111883,
"max": 0.26037654495242657,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.15999831787000102,
"min": 0.11023536945382753,
"max": 0.312678653622667,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.799991589350005,
"min": 0.4409414778153101,
"max": 1.563393268113335,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.0528989824000023e-06,
"min": 3.0528989824000023e-06,
"max": 0.00029675280108239997,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.526449491200001e-05,
"min": 1.526449491200001e-05,
"max": 0.001454064015312,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1010176,
"min": 0.1010176,
"max": 0.19891760000000003,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.505088,
"min": 0.41199040000000003,
"max": 0.984688,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.077824000000003e-05,
"min": 6.077824000000003e-05,
"max": 0.00494598824,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00030389120000000016,
"min": 0.00030389120000000016,
"max": 0.0242359312,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.745454545454546,
"min": 3.0454545454545454,
"max": 27.136363636363637,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1471.0,
"min": 134.0,
"max": 1471.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.745454545454546,
"min": 3.0454545454545454,
"max": 27.136363636363637,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1471.0,
"min": 134.0,
"max": 1471.0,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1707073132",
"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": "1707074137"
},
"total": 1004.4595029910001,
"count": 1,
"self": 0.4401578869999412,
"children": {
"run_training.setup": {
"total": 0.05153279800015298,
"count": 1,
"self": 0.05153279800015298
},
"TrainerController.start_learning": {
"total": 1003.967812306,
"count": 1,
"self": 0.9765823259951958,
"children": {
"TrainerController._reset_env": {
"total": 2.9138601119998384,
"count": 1,
"self": 2.9138601119998384
},
"TrainerController.advance": {
"total": 999.9857567700046,
"count": 45464,
"self": 1.0005640729191327,
"children": {
"env_step": {
"total": 770.3809617430652,
"count": 45464,
"self": 612.7813286580763,
"children": {
"SubprocessEnvManager._take_step": {
"total": 156.98996638902463,
"count": 45464,
"self": 3.2964207920510944,
"children": {
"TorchPolicy.evaluate": {
"total": 153.69354559697354,
"count": 45464,
"self": 153.69354559697354
}
}
},
"workers": {
"total": 0.6096666959642789,
"count": 45464,
"self": 0.0,
"children": {
"worker_root": {
"total": 1000.4984722660133,
"count": 45464,
"is_parallel": true,
"self": 462.8248077470289,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005564004999996541,
"count": 1,
"is_parallel": true,
"self": 0.003878509000287522,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001685495999709019,
"count": 10,
"is_parallel": true,
"self": 0.001685495999709019
}
}
},
"UnityEnvironment.step": {
"total": 0.03649870499998542,
"count": 1,
"is_parallel": true,
"self": 0.0006563619999724324,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004353859999355336,
"count": 1,
"is_parallel": true,
"self": 0.0004353859999355336
},
"communicator.exchange": {
"total": 0.03318390399999771,
"count": 1,
"is_parallel": true,
"self": 0.03318390399999771
},
"steps_from_proto": {
"total": 0.0022230530000797444,
"count": 1,
"is_parallel": true,
"self": 0.0003948290000153065,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018282240000644379,
"count": 10,
"is_parallel": true,
"self": 0.0018282240000644379
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 537.6736645189844,
"count": 45463,
"is_parallel": true,
"self": 27.849253886075985,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 14.857719749955322,
"count": 45463,
"is_parallel": true,
"self": 14.857719749955322
},
"communicator.exchange": {
"total": 408.24973325700194,
"count": 45463,
"is_parallel": true,
"self": 408.24973325700194
},
"steps_from_proto": {
"total": 86.71695762595118,
"count": 45463,
"is_parallel": true,
"self": 15.567385575895287,
"children": {
"_process_rank_one_or_two_observation": {
"total": 71.1495720500559,
"count": 454630,
"is_parallel": true,
"self": 71.1495720500559
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 228.6042309540203,
"count": 45464,
"self": 1.2050658750358707,
"children": {
"process_trajectory": {
"total": 67.84673713098505,
"count": 45464,
"self": 66.81431133398564,
"children": {
"RLTrainer._checkpoint": {
"total": 1.032425796999405,
"count": 10,
"self": 1.032425796999405
}
}
},
"_update_policy": {
"total": 159.55242794799938,
"count": 227,
"self": 96.90116792098843,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.65126002701095,
"count": 5448,
"self": 62.65126002701095
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1920001270482317e-06,
"count": 1,
"self": 1.1920001270482317e-06
},
"TrainerController._save_models": {
"total": 0.09161190600025293,
"count": 1,
"self": 0.0010846240002138074,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09052728200003912,
"count": 1,
"self": 0.09052728200003912
}
}
}
}
}
}
}