Alrcatraz's picture
First Push
e8af9c1 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8214641809463501,
"min": 0.8187927603721619,
"max": 2.864686965942383,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7807.1953125,
"min": 7807.1953125,
"max": 29242.724609375,
"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": 12.870420455932617,
"min": 0.20681467652320862,
"max": 12.870420455932617,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2509.73193359375,
"min": 40.122047424316406,
"max": 2616.70263671875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0693554709949097,
"min": 0.0625736385652357,
"max": 0.07622501484915048,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2774218839796388,
"min": 0.26281694137387424,
"max": 0.36030553226865936,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1728297308744753,
"min": 0.11720967476310976,
"max": 0.2915595989601285,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6913189234979012,
"min": 0.468838699052439,
"max": 1.4577979948006425,
"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": 25.363636363636363,
"min": 3.2045454545454546,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1116.0,
"min": 141.0,
"max": 1387.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.363636363636363,
"min": 3.2045454545454546,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1116.0,
"min": 141.0,
"max": 1387.0,
"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": "1739623142",
"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": "1739623566"
},
"total": 424.27597293199995,
"count": 1,
"self": 0.43900121099989065,
"children": {
"run_training.setup": {
"total": 0.029881740000064383,
"count": 1,
"self": 0.029881740000064383
},
"TrainerController.start_learning": {
"total": 423.807089981,
"count": 1,
"self": 0.34729993498888234,
"children": {
"TrainerController._reset_env": {
"total": 3.3822809880000477,
"count": 1,
"self": 3.3822809880000477
},
"TrainerController.advance": {
"total": 419.98368280701095,
"count": 18192,
"self": 0.3612036660143758,
"children": {
"env_step": {
"total": 296.2804066839948,
"count": 18192,
"self": 225.5615427219867,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.50756724800783,
"count": 18192,
"self": 1.2333199300154547,
"children": {
"TorchPolicy.evaluate": {
"total": 69.27424731799238,
"count": 18192,
"self": 69.27424731799238
}
}
},
"workers": {
"total": 0.21129671400024108,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 422.2663785069951,
"count": 18192,
"is_parallel": true,
"self": 224.91751711800077,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006293877999951292,
"count": 1,
"is_parallel": true,
"self": 0.004730824000034772,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015630539999165194,
"count": 10,
"is_parallel": true,
"self": 0.0015630539999165194
}
}
},
"UnityEnvironment.step": {
"total": 0.03526848199999222,
"count": 1,
"is_parallel": true,
"self": 0.0005989949997911026,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004117330000781294,
"count": 1,
"is_parallel": true,
"self": 0.0004117330000781294
},
"communicator.exchange": {
"total": 0.03240985700006149,
"count": 1,
"is_parallel": true,
"self": 0.03240985700006149
},
"steps_from_proto": {
"total": 0.0018478970000614936,
"count": 1,
"is_parallel": true,
"self": 0.00036309499989783944,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014848020001636542,
"count": 10,
"is_parallel": true,
"self": 0.0014848020001636542
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 197.34886138899435,
"count": 18191,
"is_parallel": true,
"self": 9.58953207100194,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.26983986798723,
"count": 18191,
"is_parallel": true,
"self": 5.26983986798723
},
"communicator.exchange": {
"total": 151.99885283700598,
"count": 18191,
"is_parallel": true,
"self": 151.99885283700598
},
"steps_from_proto": {
"total": 30.490636612999197,
"count": 18191,
"is_parallel": true,
"self": 5.4358481530071,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.054788459992096,
"count": 181910,
"is_parallel": true,
"self": 25.054788459992096
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 123.34207245700179,
"count": 18192,
"self": 0.424464123999428,
"children": {
"process_trajectory": {
"total": 26.28711642300243,
"count": 18192,
"self": 25.740740397002355,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5463760260000754,
"count": 4,
"self": 0.5463760260000754
}
}
},
"_update_policy": {
"total": 96.63049190999993,
"count": 90,
"self": 38.66453125000078,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.965960659999155,
"count": 4587,
"self": 57.965960659999155
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.340000476891873e-07,
"count": 1,
"self": 8.340000476891873e-07
},
"TrainerController._save_models": {
"total": 0.09382541700006186,
"count": 1,
"self": 0.0009355580000374175,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09288985900002444,
"count": 1,
"self": 0.09288985900002444
}
}
}
}
}
}
}