jake-snake's picture
First Push
a881ba4 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.153520345687866,
"min": 2.153520345687866,
"max": 2.8549132347106934,
"count": 5
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 21983.134765625,
"min": 21983.134765625,
"max": 29142.955078125,
"count": 5
},
"SnowballTarget.Step.mean": {
"value": 49936.0,
"min": 9952.0,
"max": 49936.0,
"count": 5
},
"SnowballTarget.Step.sum": {
"value": 49936.0,
"min": 9952.0,
"max": 49936.0,
"count": 5
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 5.117806434631348,
"min": 0.5016031265258789,
"max": 5.117806434631348,
"count": 5
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 992.8544921875,
"min": 97.3110122680664,
"max": 992.8544921875,
"count": 5
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06801266378983307,
"min": 0.06801266378983307,
"max": 0.07335259129470026,
"count": 5
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2720506551593323,
"min": 0.2720506551593323,
"max": 0.36676295647350127,
"count": 5
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2910351525334751,
"min": 0.13288198571706958,
"max": 0.2987220456787184,
"count": 5
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.1641406101339005,
"min": 0.5315279428682783,
"max": 1.4936102283935921,
"count": 5
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 0.000232482022506,
"min": 0.000232482022506,
"max": 0.000291882002706,
"count": 5
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.000929928090024,
"min": 0.000929928090024,
"max": 0.00138516003828,
"count": 5
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.17749400000000004,
"min": 0.17749400000000004,
"max": 0.19729400000000002,
"count": 5
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.7099760000000002,
"min": 0.7099760000000002,
"max": 0.96172,
"count": 5
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0038769506000000003,
"min": 0.0038769506000000003,
"max": 0.0048649706,
"count": 5
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.015507802400000001,
"min": 0.015507802400000001,
"max": 0.023089828,
"count": 5
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 5
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 5
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 14.886363636363637,
"min": 3.522727272727273,
"max": 14.886363636363637,
"count": 5
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 655.0,
"min": 155.0,
"max": 655.0,
"count": 5
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 14.886363636363637,
"min": 3.522727272727273,
"max": 14.886363636363637,
"count": 5
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 655.0,
"min": 155.0,
"max": 655.0,
"count": 5
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 5
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 5
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1760568921",
"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": "2.9.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1760569048"
},
"total": 126.58975467200003,
"count": 1,
"self": 0.48942553000017597,
"children": {
"run_training.setup": {
"total": 0.029943460999902527,
"count": 1,
"self": 0.029943460999902527
},
"TrainerController.start_learning": {
"total": 126.07038568099995,
"count": 1,
"self": 0.09919236100336093,
"children": {
"TrainerController._reset_env": {
"total": 2.9745326490000252,
"count": 1,
"self": 2.9745326490000252
},
"TrainerController.advance": {
"total": 122.96328623699651,
"count": 4592,
"self": 0.1016078020028317,
"children": {
"env_step": {
"total": 90.8613675019966,
"count": 4592,
"self": 71.33416019399942,
"children": {
"SubprocessEnvManager._take_step": {
"total": 19.46554095099657,
"count": 4592,
"self": 0.3547104159939636,
"children": {
"TorchPolicy.evaluate": {
"total": 19.110830535002606,
"count": 4592,
"self": 19.110830535002606
}
}
},
"workers": {
"total": 0.061666357000603966,
"count": 4592,
"self": 0.0,
"children": {
"worker_root": {
"total": 125.60714235300645,
"count": 4592,
"is_parallel": true,
"self": 62.76755555900195,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005064174000040111,
"count": 1,
"is_parallel": true,
"self": 0.0033472690000735383,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001716904999966573,
"count": 10,
"is_parallel": true,
"self": 0.001716904999966573
}
}
},
"UnityEnvironment.step": {
"total": 0.07805939799993666,
"count": 1,
"is_parallel": true,
"self": 0.0006936379999160636,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047787599999082886,
"count": 1,
"is_parallel": true,
"self": 0.00047787599999082886
},
"communicator.exchange": {
"total": 0.07269210899994505,
"count": 1,
"is_parallel": true,
"self": 0.07269210899994505
},
"steps_from_proto": {
"total": 0.004195775000084723,
"count": 1,
"is_parallel": true,
"self": 0.00038742900017041393,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0038083459999143088,
"count": 10,
"is_parallel": true,
"self": 0.0038083459999143088
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 62.839586794004504,
"count": 4591,
"is_parallel": true,
"self": 2.9478102020009374,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.574331990002861,
"count": 4591,
"is_parallel": true,
"self": 1.574331990002861
},
"communicator.exchange": {
"total": 47.42529596799727,
"count": 4591,
"is_parallel": true,
"self": 47.42529596799727
},
"steps_from_proto": {
"total": 10.892148634003433,
"count": 4591,
"is_parallel": true,
"self": 1.8204367310160023,
"children": {
"_process_rank_one_or_two_observation": {
"total": 9.071711902987431,
"count": 45910,
"is_parallel": true,
"self": 9.071711902987431
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 32.00031093299708,
"count": 4592,
"self": 0.11664961599910839,
"children": {
"process_trajectory": {
"total": 7.5637410089979085,
"count": 4592,
"self": 7.530290762997993,
"children": {
"RLTrainer._checkpoint": {
"total": 0.03345024599991575,
"count": 1,
"self": 0.03345024599991575
}
}
},
"_update_policy": {
"total": 24.319920308000064,
"count": 22,
"self": 10.286367948999896,
"children": {
"TorchPPOOptimizer.update": {
"total": 14.033552359000169,
"count": 1119,
"self": 14.033552359000169
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.03337443400005213,
"count": 1,
"self": 2.2535000084644707e-05,
"children": {
"RLTrainer._checkpoint": {
"total": 0.03335189899996749,
"count": 1,
"self": 0.03335189899996749
}
}
}
}
}
}
}