atomkevich's picture
First Push
a664dd2 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6883825659751892,
"min": 0.6883825659751892,
"max": 2.8438222408294678,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6542.3876953125,
"min": 6542.3876953125,
"max": 29029.73828125,
"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": 12.95618724822998,
"min": 0.3728848397731781,
"max": 12.95618724822998,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2526.45654296875,
"min": 72.33966064453125,
"max": 2626.75732421875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.059815971813804936,
"min": 0.059815971813804936,
"max": 0.07524567805824108,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.23926388725521974,
"min": 0.23926388725521974,
"max": 0.37622839029120536,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19046839038092717,
"min": 0.13122155626907067,
"max": 0.28880043196327543,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7618735615237087,
"min": 0.5248862250762827,
"max": 1.3354327880284367,
"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": 25.681818181818183,
"min": 3.6818181818181817,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1130.0,
"min": 162.0,
"max": 1401.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.681818181818183,
"min": 3.6818181818181817,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1130.0,
"min": 162.0,
"max": 1401.0,
"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": "1742559666",
"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": "1742560128"
},
"total": 462.140090589,
"count": 1,
"self": 0.4885861620000469,
"children": {
"run_training.setup": {
"total": 0.023611027000015383,
"count": 1,
"self": 0.023611027000015383
},
"TrainerController.start_learning": {
"total": 461.62789339999995,
"count": 1,
"self": 0.47334218597279687,
"children": {
"TrainerController._reset_env": {
"total": 3.2483883050001623,
"count": 1,
"self": 3.2483883050001623
},
"TrainerController.advance": {
"total": 457.81608108302703,
"count": 18192,
"self": 0.4512079060332326,
"children": {
"env_step": {
"total": 326.6605475109768,
"count": 18192,
"self": 249.51136842298274,
"children": {
"SubprocessEnvManager._take_step": {
"total": 76.87899266598833,
"count": 18192,
"self": 1.3903927039718837,
"children": {
"TorchPolicy.evaluate": {
"total": 75.48859996201645,
"count": 18192,
"self": 75.48859996201645
}
}
},
"workers": {
"total": 0.27018642200573595,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 460.0334626909985,
"count": 18192,
"is_parallel": true,
"self": 242.45018891199106,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0062127350001901505,
"count": 1,
"is_parallel": true,
"self": 0.004257152000036513,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001955583000153638,
"count": 10,
"is_parallel": true,
"self": 0.001955583000153638
}
}
},
"UnityEnvironment.step": {
"total": 0.03502480700012711,
"count": 1,
"is_parallel": true,
"self": 0.0006236260001060145,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000365077000196834,
"count": 1,
"is_parallel": true,
"self": 0.000365077000196834
},
"communicator.exchange": {
"total": 0.032206912999981796,
"count": 1,
"is_parallel": true,
"self": 0.032206912999981796
},
"steps_from_proto": {
"total": 0.0018291909998424671,
"count": 1,
"is_parallel": true,
"self": 0.0003492979994916823,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014798930003507849,
"count": 10,
"is_parallel": true,
"self": 0.0014798930003507849
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 217.5832737790074,
"count": 18191,
"is_parallel": true,
"self": 10.299423685002239,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.547313553017375,
"count": 18191,
"is_parallel": true,
"self": 5.547313553017375
},
"communicator.exchange": {
"total": 168.97552005598232,
"count": 18191,
"is_parallel": true,
"self": 168.97552005598232
},
"steps_from_proto": {
"total": 32.761016485005484,
"count": 18191,
"is_parallel": true,
"self": 6.090854869030409,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.670161615975076,
"count": 181910,
"is_parallel": true,
"self": 26.670161615975076
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 130.70432566601698,
"count": 18192,
"self": 0.6369937050217231,
"children": {
"process_trajectory": {
"total": 28.4214401099955,
"count": 18192,
"self": 27.904427119995262,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5170129900002394,
"count": 4,
"self": 0.5170129900002394
}
}
},
"_update_policy": {
"total": 101.64589185099976,
"count": 90,
"self": 40.855626346985446,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.790265504014315,
"count": 4587,
"self": 60.790265504014315
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.40000063565094e-07,
"count": 1,
"self": 9.40000063565094e-07
},
"TrainerController._save_models": {
"total": 0.09008088599989605,
"count": 1,
"self": 0.0009433149998585577,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0891375710000375,
"count": 1,
"self": 0.0891375710000375
}
}
}
}
}
}
}