soorajviraat's picture
First Push
12c8b00 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0070409774780273,
"min": 1.0070409774780273,
"max": 2.8353476524353027,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9570.9169921875,
"min": 9570.9169921875,
"max": 28943.228515625,
"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": 12.005372047424316,
"min": 0.46168285608291626,
"max": 12.005372047424316,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2341.047607421875,
"min": 89.56647491455078,
"max": 2427.34130859375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07560328901151889,
"min": 0.060975994511767675,
"max": 0.07684408723413498,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.30241315604607555,
"min": 0.25415561548217347,
"max": 0.3842204361706749,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21087645352178927,
"min": 0.12241758656569338,
"max": 0.27248252817228724,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8435058140871571,
"min": 0.4896703462627735,
"max": 1.362412640861436,
"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": 23.613636363636363,
"min": 3.590909090909091,
"max": 23.613636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1039.0,
"min": 158.0,
"max": 1283.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.613636363636363,
"min": 3.590909090909091,
"max": 23.613636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1039.0,
"min": 158.0,
"max": 1283.0,
"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": "1766131308",
"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": "1766131732"
},
"total": 424.01439784600007,
"count": 1,
"self": 0.43525676800004476,
"children": {
"run_training.setup": {
"total": 0.03486800000007406,
"count": 1,
"self": 0.03486800000007406
},
"TrainerController.start_learning": {
"total": 423.54427307799995,
"count": 1,
"self": 0.34566445199720874,
"children": {
"TrainerController._reset_env": {
"total": 3.6007997760000308,
"count": 1,
"self": 3.6007997760000308
},
"TrainerController.advance": {
"total": 419.519682145003,
"count": 18192,
"self": 0.3577469430205156,
"children": {
"env_step": {
"total": 303.12343163998673,
"count": 18192,
"self": 237.42160192998426,
"children": {
"SubprocessEnvManager._take_step": {
"total": 65.49666606400365,
"count": 18192,
"self": 1.1839556010086199,
"children": {
"TorchPolicy.evaluate": {
"total": 64.31271046299503,
"count": 18192,
"self": 64.31271046299503
}
}
},
"workers": {
"total": 0.20516364599882309,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 421.7214043819921,
"count": 18192,
"is_parallel": true,
"self": 213.17673191099482,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007215883999947437,
"count": 1,
"is_parallel": true,
"self": 0.005214103000184878,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002001780999762559,
"count": 10,
"is_parallel": true,
"self": 0.002001780999762559
}
}
},
"UnityEnvironment.step": {
"total": 0.03415669899993645,
"count": 1,
"is_parallel": true,
"self": 0.0005755349997116355,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038056100004268956,
"count": 1,
"is_parallel": true,
"self": 0.00038056100004268956
},
"communicator.exchange": {
"total": 0.031323920000090766,
"count": 1,
"is_parallel": true,
"self": 0.031323920000090766
},
"steps_from_proto": {
"total": 0.0018766830000913615,
"count": 1,
"is_parallel": true,
"self": 0.00037482000016098027,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015018629999303812,
"count": 10,
"is_parallel": true,
"self": 0.0015018629999303812
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 208.54467247099728,
"count": 18191,
"is_parallel": true,
"self": 10.009323952001068,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.292309070008514,
"count": 18191,
"is_parallel": true,
"self": 5.292309070008514
},
"communicator.exchange": {
"total": 159.1521367839972,
"count": 18191,
"is_parallel": true,
"self": 159.1521367839972
},
"steps_from_proto": {
"total": 34.090902664990494,
"count": 18191,
"is_parallel": true,
"self": 6.290187477956806,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.80071518703369,
"count": 181910,
"is_parallel": true,
"self": 27.80071518703369
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 116.03850356199575,
"count": 18192,
"self": 0.4410162670008049,
"children": {
"process_trajectory": {
"total": 25.078795808995096,
"count": 18192,
"self": 24.590604888995017,
"children": {
"RLTrainer._checkpoint": {
"total": 0.48819092000007913,
"count": 4,
"self": 0.48819092000007913
}
}
},
"_update_policy": {
"total": 90.51869148599985,
"count": 90,
"self": 36.96337544599942,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.555316040000434,
"count": 4587,
"self": 53.555316040000434
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0069998097606003e-06,
"count": 1,
"self": 1.0069998097606003e-06
},
"TrainerController._save_models": {
"total": 0.07812569799989433,
"count": 1,
"self": 0.0006705639998472179,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07745513400004711,
"count": 1,
"self": 0.07745513400004711
}
}
}
}
}
}
}