CHarthikReddy's picture
First try
0379996 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7518959641456604,
"min": 0.7518959641456604,
"max": 2.839890718460083,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7146.01904296875,
"min": 7146.01904296875,
"max": 28989.603515625,
"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": 12.163474082946777,
"min": 0.25736936926841736,
"max": 12.163474082946777,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2371.87744140625,
"min": 49.929656982421875,
"max": 2466.13037109375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06751001392445223,
"min": 0.0632901023628245,
"max": 0.07511176096240887,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2700400556978089,
"min": 0.253160409451298,
"max": 0.3755588048120444,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1813097558185166,
"min": 0.10995522335025609,
"max": 0.2885720038823053,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7252390232740664,
"min": 0.43982089340102437,
"max": 1.3869632789317299,
"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": 0.10538800000000001,
"min": 0.10538800000000001,
"max": 0.29458799999999996,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.42155200000000004,
"min": 0.42155200000000004,
"max": 1.42344,
"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": 24.045454545454547,
"min": 3.0454545454545454,
"max": 24.236363636363638,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1058.0,
"min": 134.0,
"max": 1333.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.045454545454547,
"min": 3.0454545454545454,
"max": 24.236363636363638,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1058.0,
"min": 134.0,
"max": 1333.0,
"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": "1768798587",
"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": "1768799053"
},
"total": 466.1092507960002,
"count": 1,
"self": 0.4853179220003767,
"children": {
"run_training.setup": {
"total": 0.026527401999828726,
"count": 1,
"self": 0.026527401999828726
},
"TrainerController.start_learning": {
"total": 465.597405472,
"count": 1,
"self": 0.3652373710078791,
"children": {
"TrainerController._reset_env": {
"total": 3.67170717099998,
"count": 1,
"self": 3.67170717099998
},
"TrainerController.advance": {
"total": 461.47771115799196,
"count": 18192,
"self": 0.3954642859903288,
"children": {
"env_step": {
"total": 336.08401588399784,
"count": 18192,
"self": 262.44123725694044,
"children": {
"SubprocessEnvManager._take_step": {
"total": 73.42292265201831,
"count": 18192,
"self": 1.3027563540317715,
"children": {
"TorchPolicy.evaluate": {
"total": 72.12016629798654,
"count": 18192,
"self": 72.12016629798654
}
}
},
"workers": {
"total": 0.21985597503908139,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 463.93305835804176,
"count": 18192,
"is_parallel": true,
"self": 233.00500966099753,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00554085900012069,
"count": 1,
"is_parallel": true,
"self": 0.004053231999478157,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001487627000642533,
"count": 10,
"is_parallel": true,
"self": 0.001487627000642533
}
}
},
"UnityEnvironment.step": {
"total": 0.03787581999995382,
"count": 1,
"is_parallel": true,
"self": 0.0005893179995837272,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004264730000613781,
"count": 1,
"is_parallel": true,
"self": 0.0004264730000613781
},
"communicator.exchange": {
"total": 0.034622081000179605,
"count": 1,
"is_parallel": true,
"self": 0.034622081000179605
},
"steps_from_proto": {
"total": 0.0022379480001291086,
"count": 1,
"is_parallel": true,
"self": 0.00045223400002214476,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017857140001069638,
"count": 10,
"is_parallel": true,
"self": 0.0017857140001069638
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 230.92804869704423,
"count": 18191,
"is_parallel": true,
"self": 10.992721490037184,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.87340987502148,
"count": 18191,
"is_parallel": true,
"self": 5.87340987502148
},
"communicator.exchange": {
"total": 174.73282384500772,
"count": 18191,
"is_parallel": true,
"self": 174.73282384500772
},
"steps_from_proto": {
"total": 39.329093486977854,
"count": 18191,
"is_parallel": true,
"self": 6.892069995991733,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.43702349098612,
"count": 181910,
"is_parallel": true,
"self": 32.43702349098612
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 124.9982309880038,
"count": 18192,
"self": 0.4603622949553028,
"children": {
"process_trajectory": {
"total": 28.626828592046877,
"count": 18192,
"self": 28.14845604304628,
"children": {
"RLTrainer._checkpoint": {
"total": 0.47837254900059634,
"count": 4,
"self": 0.47837254900059634
}
}
},
"_update_policy": {
"total": 95.91104010100162,
"count": 90,
"self": 39.66992216201152,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.2411179389901,
"count": 4587,
"self": 56.2411179389901
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1090000953117851e-06,
"count": 1,
"self": 1.1090000953117851e-06
},
"TrainerController._save_models": {
"total": 0.08274866300007488,
"count": 1,
"self": 0.0007225589997688076,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08202610400030608,
"count": 1,
"self": 0.08202610400030608
}
}
}
}
}
}
}