Lyuhong's picture
First Push
3f69df4 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9701952934265137,
"min": 0.9701952934265137,
"max": 2.8699159622192383,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9263.4248046875,
"min": 9263.4248046875,
"max": 29517.0859375,
"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": 12.762807846069336,
"min": 0.2961099445819855,
"max": 12.762807846069336,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2488.74755859375,
"min": 57.44532775878906,
"max": 2588.3330078125,
"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.Losses.PolicyLoss.mean": {
"value": 0.0641456055483443,
"min": 0.06320922957224243,
"max": 0.07281320248701947,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2565824221933772,
"min": 0.2565824221933772,
"max": 0.36406601243509734,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22446480276537878,
"min": 0.10607425156551614,
"max": 0.2751008603502722,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8978592110615151,
"min": 0.42429700626206457,
"max": 1.375504301751361,
"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.CumulativeReward.mean": {
"value": 24.84090909090909,
"min": 3.0,
"max": 25.254545454545454,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1093.0,
"min": 132.0,
"max": 1389.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.84090909090909,
"min": 3.0,
"max": 25.254545454545454,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1093.0,
"min": 132.0,
"max": 1389.0,
"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": "1722574883",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1722575336"
},
"total": 453.4173591350001,
"count": 1,
"self": 0.4246600770001123,
"children": {
"run_training.setup": {
"total": 0.0504650139999967,
"count": 1,
"self": 0.0504650139999967
},
"TrainerController.start_learning": {
"total": 452.942234044,
"count": 1,
"self": 0.5686279240155727,
"children": {
"TrainerController._reset_env": {
"total": 1.6113369579999244,
"count": 1,
"self": 1.6113369579999244
},
"TrainerController.advance": {
"total": 450.6681912039844,
"count": 18201,
"self": 0.2671992669852443,
"children": {
"env_step": {
"total": 450.40099193699916,
"count": 18201,
"self": 292.76070303799827,
"children": {
"SubprocessEnvManager._take_step": {
"total": 157.36217478099957,
"count": 18201,
"self": 1.4816806079843445,
"children": {
"TorchPolicy.evaluate": {
"total": 155.88049417301522,
"count": 18201,
"self": 155.88049417301522
}
}
},
"workers": {
"total": 0.27811411800132646,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 451.77209152202045,
"count": 18201,
"is_parallel": true,
"self": 227.06605965002666,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022923930000615655,
"count": 1,
"is_parallel": true,
"self": 0.0007166720002942384,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015757209997673272,
"count": 10,
"is_parallel": true,
"self": 0.0015757209997673272
}
}
},
"UnityEnvironment.step": {
"total": 0.03855562599994755,
"count": 1,
"is_parallel": true,
"self": 0.0006331769999405878,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039610700002867816,
"count": 1,
"is_parallel": true,
"self": 0.00039610700002867816
},
"communicator.exchange": {
"total": 0.035491557000000284,
"count": 1,
"is_parallel": true,
"self": 0.035491557000000284
},
"steps_from_proto": {
"total": 0.002034784999978001,
"count": 1,
"is_parallel": true,
"self": 0.00038572299979477975,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016490620001832212,
"count": 10,
"is_parallel": true,
"self": 0.0016490620001832212
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 224.7060318719938,
"count": 18200,
"is_parallel": true,
"self": 10.055586800979086,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.4451712100086525,
"count": 18200,
"is_parallel": true,
"self": 5.4451712100086525
},
"communicator.exchange": {
"total": 175.55589529899623,
"count": 18200,
"is_parallel": true,
"self": 175.55589529899623
},
"steps_from_proto": {
"total": 33.649378562009815,
"count": 18200,
"is_parallel": true,
"self": 6.4074955819737625,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.241882980036053,
"count": 182000,
"is_parallel": true,
"self": 27.241882980036053
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012106999997740786,
"count": 1,
"self": 0.00012106999997740786,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 445.14493577497353,
"count": 673037,
"is_parallel": true,
"self": 13.920244886934029,
"children": {
"process_trajectory": {
"total": 246.6602226940406,
"count": 673037,
"is_parallel": true,
"self": 245.8322484230407,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8279742709999027,
"count": 4,
"is_parallel": true,
"self": 0.8279742709999027
}
}
},
"_update_policy": {
"total": 184.5644681939989,
"count": 90,
"is_parallel": true,
"self": 56.3542547920041,
"children": {
"TorchPPOOptimizer.update": {
"total": 128.2102134019948,
"count": 4587,
"is_parallel": true,
"self": 128.2102134019948
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09395688800009339,
"count": 1,
"self": 0.0012031170001591818,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0927537709999342,
"count": 1,
"self": 0.0927537709999342
}
}
}
}
}
}
}