HarryStot's picture
First Push
4ab85cd verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7165364027023315,
"min": 0.7165364027023315,
"max": 2.8673012256622314,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6809.9619140625,
"min": 6809.9619140625,
"max": 29269.41015625,
"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": 13.048495292663574,
"min": 0.5250157713890076,
"max": 13.048495292663574,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2544.45654296875,
"min": 101.85305786132812,
"max": 2619.876708984375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06662506312725372,
"min": 0.06177080560158299,
"max": 0.07877504601228615,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2665002525090149,
"min": 0.26188398147796227,
"max": 0.3552987589833255,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19840625476311236,
"min": 0.11992477570368232,
"max": 0.2924627550676757,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7936250190524494,
"min": 0.4796991028147293,
"max": 1.4102643441920186,
"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": 25.84090909090909,
"min": 3.5681818181818183,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1137.0,
"min": 157.0,
"max": 1405.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.84090909090909,
"min": 3.5681818181818183,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1137.0,
"min": 157.0,
"max": 1405.0,
"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": "1757926988",
"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": "1757927404"
},
"total": 415.502443816,
"count": 1,
"self": 0.7879848390000461,
"children": {
"run_training.setup": {
"total": 0.024676779999936116,
"count": 1,
"self": 0.024676779999936116
},
"TrainerController.start_learning": {
"total": 414.689782197,
"count": 1,
"self": 0.3420563579973077,
"children": {
"TrainerController._reset_env": {
"total": 2.764964020999969,
"count": 1,
"self": 2.764964020999969
},
"TrainerController.advance": {
"total": 411.46707207700285,
"count": 18192,
"self": 0.35798217101319096,
"children": {
"env_step": {
"total": 294.20315278199814,
"count": 18192,
"self": 226.14971458801915,
"children": {
"SubprocessEnvManager._take_step": {
"total": 67.8452953939991,
"count": 18192,
"self": 1.2287328089940956,
"children": {
"TorchPolicy.evaluate": {
"total": 66.616562585005,
"count": 18192,
"self": 66.616562585005
}
}
},
"workers": {
"total": 0.20814279997989615,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 413.2743762179979,
"count": 18192,
"is_parallel": true,
"self": 214.89254432998518,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005638599999997496,
"count": 1,
"is_parallel": true,
"self": 0.004294629000241912,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013439709997555838,
"count": 10,
"is_parallel": true,
"self": 0.0013439709997555838
}
}
},
"UnityEnvironment.step": {
"total": 0.04025377899995419,
"count": 1,
"is_parallel": true,
"self": 0.0005499599998302074,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040116500008480216,
"count": 1,
"is_parallel": true,
"self": 0.00040116500008480216
},
"communicator.exchange": {
"total": 0.03753015699999196,
"count": 1,
"is_parallel": true,
"self": 0.03753015699999196
},
"steps_from_proto": {
"total": 0.001772497000047224,
"count": 1,
"is_parallel": true,
"self": 0.00033221900014268613,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014402779999045379,
"count": 10,
"is_parallel": true,
"self": 0.0014402779999045379
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 198.3818318880127,
"count": 18191,
"is_parallel": true,
"self": 9.704610639035536,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.325398140999596,
"count": 18191,
"is_parallel": true,
"self": 5.325398140999596
},
"communicator.exchange": {
"total": 152.29807952199383,
"count": 18191,
"is_parallel": true,
"self": 152.29807952199383
},
"steps_from_proto": {
"total": 31.05374358598374,
"count": 18191,
"is_parallel": true,
"self": 5.517495791005217,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.53624779497852,
"count": 181910,
"is_parallel": true,
"self": 25.53624779497852
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 116.90593712399152,
"count": 18192,
"self": 0.42288014600501356,
"children": {
"process_trajectory": {
"total": 26.057863247986006,
"count": 18192,
"self": 25.593552434985895,
"children": {
"RLTrainer._checkpoint": {
"total": 0.464310813000111,
"count": 4,
"self": 0.464310813000111
}
}
},
"_update_policy": {
"total": 90.4251937300005,
"count": 90,
"self": 36.820326000007526,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.604867729992975,
"count": 4587,
"self": 53.604867729992975
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0969999948429177e-06,
"count": 1,
"self": 1.0969999948429177e-06
},
"TrainerController._save_models": {
"total": 0.11568864399987433,
"count": 1,
"self": 0.0009943219999968278,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1146943219998775,
"count": 1,
"self": 0.1146943219998775
}
}
}
}
}
}
}