Bavantha11's picture
First Push
75c7ab5 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7720561027526855,
"min": 0.7720561027526855,
"max": 2.8590195178985596,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7337.62109375,
"min": 7337.62109375,
"max": 29184.87109375,
"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": 13.126409530639648,
"min": 0.33192530274391174,
"max": 13.126409530639648,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2559.64990234375,
"min": 64.39350891113281,
"max": 2665.65771484375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06609401159495938,
"min": 0.06272494696524661,
"max": 0.07537755841781915,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2643760463798375,
"min": 0.25089978786098643,
"max": 0.37688779208909573,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17855144529512118,
"min": 0.13391865402181616,
"max": 0.2973116506986758,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7142057811804847,
"min": 0.5356746160872646,
"max": 1.4121825288908156,
"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": 25.818181818181817,
"min": 3.7045454545454546,
"max": 25.818181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1136.0,
"min": 163.0,
"max": 1419.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.818181818181817,
"min": 3.7045454545454546,
"max": 25.818181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1136.0,
"min": 163.0,
"max": 1419.0,
"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": "1758790956",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1758791371"
},
"total": 415.12864006199993,
"count": 1,
"self": 0.43284801299989795,
"children": {
"run_training.setup": {
"total": 0.026595777000011367,
"count": 1,
"self": 0.026595777000011367
},
"TrainerController.start_learning": {
"total": 414.669196272,
"count": 1,
"self": 0.3249640630150452,
"children": {
"TrainerController._reset_env": {
"total": 2.956478178999987,
"count": 1,
"self": 2.956478178999987
},
"TrainerController.advance": {
"total": 411.270421981985,
"count": 18192,
"self": 0.3324335879975706,
"children": {
"env_step": {
"total": 296.1546765179828,
"count": 18192,
"self": 231.56194925601392,
"children": {
"SubprocessEnvManager._take_step": {
"total": 64.39563858398287,
"count": 18192,
"self": 1.1764086599789607,
"children": {
"TorchPolicy.evaluate": {
"total": 63.21922992400391,
"count": 18192,
"self": 63.21922992400391
}
}
},
"workers": {
"total": 0.1970886779860166,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 412.7281452709991,
"count": 18192,
"is_parallel": true,
"self": 209.2693517660107,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005229164000070341,
"count": 1,
"is_parallel": true,
"self": 0.003784923000125673,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014442409999446681,
"count": 10,
"is_parallel": true,
"self": 0.0014442409999446681
}
}
},
"UnityEnvironment.step": {
"total": 0.03409035799995763,
"count": 1,
"is_parallel": true,
"self": 0.0005670560000226033,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037869799996315123,
"count": 1,
"is_parallel": true,
"self": 0.00037869799996315123
},
"communicator.exchange": {
"total": 0.031374952999954075,
"count": 1,
"is_parallel": true,
"self": 0.031374952999954075
},
"steps_from_proto": {
"total": 0.0017696510000178023,
"count": 1,
"is_parallel": true,
"self": 0.0003563950002671845,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014132559997506178,
"count": 10,
"is_parallel": true,
"self": 0.0014132559997506178
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 203.45879350498842,
"count": 18191,
"is_parallel": true,
"self": 9.743054419971259,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.059741160004023,
"count": 18191,
"is_parallel": true,
"self": 5.059741160004023
},
"communicator.exchange": {
"total": 155.0088493570073,
"count": 18191,
"is_parallel": true,
"self": 155.0088493570073
},
"steps_from_proto": {
"total": 33.64714856800583,
"count": 18191,
"is_parallel": true,
"self": 6.1819426040085546,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.465205963997278,
"count": 181910,
"is_parallel": true,
"self": 27.465205963997278
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 114.78331187600463,
"count": 18192,
"self": 0.39837004200262527,
"children": {
"process_trajectory": {
"total": 24.98942773300223,
"count": 18192,
"self": 24.548934296002244,
"children": {
"RLTrainer._checkpoint": {
"total": 0.44049343699998644,
"count": 4,
"self": 0.44049343699998644
}
}
},
"_update_policy": {
"total": 89.39551410099978,
"count": 90,
"self": 36.361466507001865,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.03404759399791,
"count": 4587,
"self": 53.03404759399791
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2909999895782676e-06,
"count": 1,
"self": 1.2909999895782676e-06
},
"TrainerController._save_models": {
"total": 0.11733075699999063,
"count": 1,
"self": 0.000651501999982429,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1166792550000082,
"count": 1,
"self": 0.1166792550000082
}
}
}
}
}
}
}