MikeZ3's picture
First Push
e1e0b42 verified
Raw
History Blame Contribute Delete
17.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.856088399887085,
"min": 0.856088399887085,
"max": 2.8640546798706055,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8136.26416015625,
"min": 8136.26416015625,
"max": 29236.26953125,
"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": 13.076863288879395,
"min": 0.31409552693367004,
"max": 13.076863288879395,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2549.98828125,
"min": 60.934532165527344,
"max": 2649.066162109375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06749855435227088,
"min": 0.06189213045587416,
"max": 0.07229792057997639,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2699942174090835,
"min": 0.25352567079443916,
"max": 0.3614896028998819,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20169559800449538,
"min": 0.10209751746493995,
"max": 0.30438092047092963,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8067823920179815,
"min": 0.4083900698597598,
"max": 1.521904602354648,
"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": 25.545454545454547,
"min": 2.8863636363636362,
"max": 25.6,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1124.0,
"min": 127.0,
"max": 1408.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.545454545454547,
"min": 2.8863636363636362,
"max": 25.6,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1124.0,
"min": 127.0,
"max": 1408.0,
"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": "1741626125",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1741626635"
},
"total": 509.75657889600006,
"count": 1,
"self": 0.4856227520001539,
"children": {
"run_training.setup": {
"total": 0.025994841000056113,
"count": 1,
"self": 0.025994841000056113
},
"TrainerController.start_learning": {
"total": 509.24496130299985,
"count": 1,
"self": 0.4470145469961153,
"children": {
"TrainerController._reset_env": {
"total": 3.5994711649998408,
"count": 1,
"self": 3.5994711649998408
},
"TrainerController.advance": {
"total": 505.0852763870039,
"count": 18192,
"self": 0.4754590399809331,
"children": {
"env_step": {
"total": 363.9834163780324,
"count": 18192,
"self": 276.27711948405545,
"children": {
"SubprocessEnvManager._take_step": {
"total": 87.43268352098698,
"count": 18192,
"self": 1.5349369559928618,
"children": {
"TorchPolicy.evaluate": {
"total": 85.89774656499412,
"count": 18192,
"self": 85.89774656499412
}
}
},
"workers": {
"total": 0.2736133729899848,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 507.430063005007,
"count": 18192,
"is_parallel": true,
"self": 265.8912078670053,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00718413699996745,
"count": 1,
"is_parallel": true,
"self": 0.00453048399981526,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0026536530001521896,
"count": 10,
"is_parallel": true,
"self": 0.0026536530001521896
}
}
},
"UnityEnvironment.step": {
"total": 0.07114337699999851,
"count": 1,
"is_parallel": true,
"self": 0.0006783960000120715,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004261639999185718,
"count": 1,
"is_parallel": true,
"self": 0.0004261639999185718
},
"communicator.exchange": {
"total": 0.06776503300011427,
"count": 1,
"is_parallel": true,
"self": 0.06776503300011427
},
"steps_from_proto": {
"total": 0.0022737839999535936,
"count": 1,
"is_parallel": true,
"self": 0.00046671700010847417,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018070669998451194,
"count": 10,
"is_parallel": true,
"self": 0.0018070669998451194
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 241.53885513800174,
"count": 18191,
"is_parallel": true,
"self": 11.604535519013098,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.557112655997798,
"count": 18191,
"is_parallel": true,
"self": 6.557112655997798
},
"communicator.exchange": {
"total": 184.75944606598864,
"count": 18191,
"is_parallel": true,
"self": 184.75944606598864
},
"steps_from_proto": {
"total": 38.6177608970022,
"count": 18191,
"is_parallel": true,
"self": 7.116629014991759,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.50113188201044,
"count": 181910,
"is_parallel": true,
"self": 31.50113188201044
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 140.62640096899054,
"count": 18192,
"self": 0.5590505280138132,
"children": {
"process_trajectory": {
"total": 30.97732536797821,
"count": 18192,
"self": 30.376168807978274,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6011565599999358,
"count": 4,
"self": 0.6011565599999358
}
}
},
"_update_policy": {
"total": 109.09002507299851,
"count": 90,
"self": 44.49941935999368,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.59060571300483,
"count": 4587,
"self": 64.59060571300483
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3530000160244526e-06,
"count": 1,
"self": 1.3530000160244526e-06
},
"TrainerController._save_models": {
"total": 0.11319785099999535,
"count": 1,
"self": 0.0010005579999869951,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11219729300000836,
"count": 1,
"self": 0.11219729300000836
}
}
}
}
}
}
}