SungjunEom's picture
First Push
e9cc5e3 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9552198052406311,
"min": 0.9377347230911255,
"max": 2.8689539432525635,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9120.4384765625,
"min": 9114.9765625,
"max": 29380.95703125,
"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": 13.10094928741455,
"min": 0.43686187267303467,
"max": 13.10094928741455,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2554.68505859375,
"min": 84.75120544433594,
"max": 2651.8486328125,
"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": 0.06570779004002415,
"min": 0.06439468302914084,
"max": 0.08125016902340576,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2628311601600966,
"min": 0.2592175569517684,
"max": 0.3705710190674747,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2291214907286214,
"min": 0.09739843586245187,
"max": 0.27942310519078195,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9164859629144856,
"min": 0.38959374344980746,
"max": 1.3971155259539099,
"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": 25.5,
"min": 3.1136363636363638,
"max": 25.98181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1122.0,
"min": 137.0,
"max": 1429.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.5,
"min": 3.1136363636363638,
"max": 25.98181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1122.0,
"min": 137.0,
"max": 1429.0,
"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": "1707458090",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1707458512"
},
"total": 421.93407022600013,
"count": 1,
"self": 0.43941270799996346,
"children": {
"run_training.setup": {
"total": 0.0485740540000279,
"count": 1,
"self": 0.0485740540000279
},
"TrainerController.start_learning": {
"total": 421.44608346400014,
"count": 1,
"self": 0.5251830050183344,
"children": {
"TrainerController._reset_env": {
"total": 2.999170948000028,
"count": 1,
"self": 2.999170948000028
},
"TrainerController.advance": {
"total": 417.83334616798174,
"count": 18198,
"self": 0.24139086199033954,
"children": {
"env_step": {
"total": 417.5919553059914,
"count": 18198,
"self": 268.01121428995634,
"children": {
"SubprocessEnvManager._take_step": {
"total": 149.3133254750096,
"count": 18198,
"self": 1.4086742670181138,
"children": {
"TorchPolicy.evaluate": {
"total": 147.9046512079915,
"count": 18198,
"self": 147.9046512079915
}
}
},
"workers": {
"total": 0.26741554102545706,
"count": 18198,
"self": 0.0,
"children": {
"worker_root": {
"total": 420.41210892900995,
"count": 18198,
"is_parallel": true,
"self": 209.13841014099603,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004819560999976602,
"count": 1,
"is_parallel": true,
"self": 0.0033638760000940238,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014556849998825783,
"count": 10,
"is_parallel": true,
"self": 0.0014556849998825783
}
}
},
"UnityEnvironment.step": {
"total": 0.03575690200000281,
"count": 1,
"is_parallel": true,
"self": 0.0006309420000434329,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038894099998287857,
"count": 1,
"is_parallel": true,
"self": 0.00038894099998287857
},
"communicator.exchange": {
"total": 0.03285421700002189,
"count": 1,
"is_parallel": true,
"self": 0.03285421700002189
},
"steps_from_proto": {
"total": 0.0018828019999546086,
"count": 1,
"is_parallel": true,
"self": 0.0003559199994924711,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015268820004621375,
"count": 10,
"is_parallel": true,
"self": 0.0015268820004621375
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 211.27369878801392,
"count": 18197,
"is_parallel": true,
"self": 10.322229160005463,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.143976516985958,
"count": 18197,
"is_parallel": true,
"self": 5.143976516985958
},
"communicator.exchange": {
"total": 163.3886788930181,
"count": 18197,
"is_parallel": true,
"self": 163.3886788930181
},
"steps_from_proto": {
"total": 32.4188142180044,
"count": 18197,
"is_parallel": true,
"self": 5.839521358975389,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.57929285902901,
"count": 181970,
"is_parallel": true,
"self": 26.57929285902901
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00017224599992005096,
"count": 1,
"self": 0.00017224599992005096,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 412.6180790159624,
"count": 655838,
"is_parallel": true,
"self": 13.283328245081066,
"children": {
"process_trajectory": {
"total": 226.6904038988805,
"count": 655838,
"is_parallel": true,
"self": 226.2014019768808,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4890019219997157,
"count": 4,
"is_parallel": true,
"self": 0.4890019219997157
}
}
},
"_update_policy": {
"total": 172.64434687200082,
"count": 90,
"is_parallel": true,
"self": 50.04047437800091,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.60387249399992,
"count": 4587,
"is_parallel": true,
"self": 122.60387249399992
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0882110970001122,
"count": 1,
"self": 0.0010118590000729455,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08719923800003926,
"count": 1,
"self": 0.08719923800003926
}
}
}
}
}
}
}