gbeane66's picture
First Push
f8ab216 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.2405688762664795,
"min": 1.2405688762664795,
"max": 2.8888485431671143,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 11790.3662109375,
"min": 11790.3662109375,
"max": 29505.73828125,
"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": 9.308652877807617,
"min": 0.25001972913742065,
"max": 9.308652877807617,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1815.187255859375,
"min": 48.50382995605469,
"max": 1868.33935546875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.029698061745421,
"min": 0.02421698381901175,
"max": 0.036461654005203556,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.118792246981684,
"min": 0.096867935276047,
"max": 0.18230827002601777,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2708836570382118,
"min": 0.08610135146106283,
"max": 0.30968329111735027,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.0835346281528473,
"min": 0.34440540584425133,
"max": 1.5484164555867512,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 5.388097306000004e-06,
"min": 5.388097306000004e-06,
"max": 0.00019458800270600002,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.1552389224000015e-05,
"min": 2.1552389224000015e-05,
"max": 0.0009234400382800001,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.102694,
"min": 0.102694,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.410776,
"min": 0.410776,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014443060000000012,
"min": 0.00014443060000000012,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000005,
"min": 0.0005777224000000005,
"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": 18.113636363636363,
"min": 2.409090909090909,
"max": 18.618181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 797.0,
"min": 106.0,
"max": 1024.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 18.113636363636363,
"min": 2.409090909090909,
"max": 18.618181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 797.0,
"min": 106.0,
"max": 1024.0,
"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": "1755845614",
"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": "1755846011"
},
"total": 397.210523073,
"count": 1,
"self": 0.4359317009999586,
"children": {
"run_training.setup": {
"total": 0.025573353000027055,
"count": 1,
"self": 0.025573353000027055
},
"TrainerController.start_learning": {
"total": 396.749018019,
"count": 1,
"self": 0.4171510860002172,
"children": {
"TrainerController._reset_env": {
"total": 3.550530594999941,
"count": 1,
"self": 3.550530594999941
},
"TrainerController.advance": {
"total": 392.6977184719997,
"count": 18192,
"self": 0.4058396859957156,
"children": {
"env_step": {
"total": 311.8840553270003,
"count": 18192,
"self": 240.1394379770029,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.49176198200166,
"count": 18192,
"self": 1.333122200005164,
"children": {
"TorchPolicy.evaluate": {
"total": 70.1586397819965,
"count": 18192,
"self": 70.1586397819965
}
}
},
"workers": {
"total": 0.2528553679957213,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 395.3373097619974,
"count": 18192,
"is_parallel": true,
"self": 185.33572737498582,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005826352999974915,
"count": 1,
"is_parallel": true,
"self": 0.004181215000130578,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016451379998443372,
"count": 10,
"is_parallel": true,
"self": 0.0016451379998443372
}
}
},
"UnityEnvironment.step": {
"total": 0.035162428999910844,
"count": 1,
"is_parallel": true,
"self": 0.000602194999942185,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041752000004180445,
"count": 1,
"is_parallel": true,
"self": 0.00041752000004180445
},
"communicator.exchange": {
"total": 0.03227983099998255,
"count": 1,
"is_parallel": true,
"self": 0.03227983099998255
},
"steps_from_proto": {
"total": 0.0018628829999443042,
"count": 1,
"is_parallel": true,
"self": 0.0003846229999453499,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014782599999989543,
"count": 10,
"is_parallel": true,
"self": 0.0014782599999989543
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 210.00158238701158,
"count": 18191,
"is_parallel": true,
"self": 10.051568329024462,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.457373601001905,
"count": 18191,
"is_parallel": true,
"self": 5.457373601001905
},
"communicator.exchange": {
"total": 162.75093714098784,
"count": 18191,
"is_parallel": true,
"self": 162.75093714098784
},
"steps_from_proto": {
"total": 31.74170331599737,
"count": 18191,
"is_parallel": true,
"self": 5.781086327997059,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.96061698800031,
"count": 181910,
"is_parallel": true,
"self": 25.96061698800031
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 80.40782345900368,
"count": 18192,
"self": 0.5395231640047768,
"children": {
"process_trajectory": {
"total": 26.144169965999254,
"count": 18192,
"self": 25.74372189299936,
"children": {
"RLTrainer._checkpoint": {
"total": 0.40044807299989316,
"count": 4,
"self": 0.40044807299989316
}
}
},
"_update_policy": {
"total": 53.72413032899965,
"count": 90,
"self": 37.330148263999945,
"children": {
"TorchPPOOptimizer.update": {
"total": 16.393982064999705,
"count": 1080,
"self": 16.393982064999705
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.02400008472614e-06,
"count": 1,
"self": 1.02400008472614e-06
},
"TrainerController._save_models": {
"total": 0.08361684200008312,
"count": 1,
"self": 0.0008219350000899794,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08279490699999315,
"count": 1,
"self": 0.08279490699999315
}
}
}
}
}
}
}