hey-its-nk's picture
First Push
be63349 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8683018684387207,
"min": 0.8683018684387207,
"max": 2.8631818294525146,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8252.3408203125,
"min": 8252.3408203125,
"max": 29227.359375,
"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": 12.726290702819824,
"min": 0.3273921608924866,
"max": 12.726290702819824,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2481.626708984375,
"min": 63.51408004760742,
"max": 2557.9638671875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06668102772199941,
"min": 0.06094213921928267,
"max": 0.07731261594225561,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26672411088799763,
"min": 0.253708837341572,
"max": 0.38656307971127807,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19151315713922185,
"min": 0.12764670219564556,
"max": 0.2933848971245336,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7660526285568874,
"min": 0.5105868087825822,
"max": 1.466924485622668,
"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": 25.34090909090909,
"min": 3.5,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1115.0,
"min": 154.0,
"max": 1356.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.34090909090909,
"min": 3.5,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1115.0,
"min": 154.0,
"max": 1356.0,
"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": "1752593804",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1752594281"
},
"total": 476.92975481999997,
"count": 1,
"self": 0.6862904419999722,
"children": {
"run_training.setup": {
"total": 0.023657889999981307,
"count": 1,
"self": 0.023657889999981307
},
"TrainerController.start_learning": {
"total": 476.219806488,
"count": 1,
"self": 0.4293912290016806,
"children": {
"TrainerController._reset_env": {
"total": 3.2240071009999838,
"count": 1,
"self": 3.2240071009999838
},
"TrainerController.advance": {
"total": 472.4287136149984,
"count": 18192,
"self": 0.45407658600458944,
"children": {
"env_step": {
"total": 344.7468136970024,
"count": 18192,
"self": 265.1701862320167,
"children": {
"SubprocessEnvManager._take_step": {
"total": 79.31714753898791,
"count": 18192,
"self": 1.4431565969607618,
"children": {
"TorchPolicy.evaluate": {
"total": 77.87399094202715,
"count": 18192,
"self": 77.87399094202715
}
}
},
"workers": {
"total": 0.25947992599776626,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 474.1087614639987,
"count": 18192,
"is_parallel": true,
"self": 241.92624973798252,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005173049000063656,
"count": 1,
"is_parallel": true,
"self": 0.003745001000083903,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014280479999797535,
"count": 10,
"is_parallel": true,
"self": 0.0014280479999797535
}
}
},
"UnityEnvironment.step": {
"total": 0.04374342999994951,
"count": 1,
"is_parallel": true,
"self": 0.0007732060000762431,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042048799991789565,
"count": 1,
"is_parallel": true,
"self": 0.00042048799991789565
},
"communicator.exchange": {
"total": 0.03990008699997816,
"count": 1,
"is_parallel": true,
"self": 0.03990008699997816
},
"steps_from_proto": {
"total": 0.0026496489999772166,
"count": 1,
"is_parallel": true,
"self": 0.00045082200006163475,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002198826999915582,
"count": 10,
"is_parallel": true,
"self": 0.002198826999915582
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 232.18251172601617,
"count": 18191,
"is_parallel": true,
"self": 10.733577260989478,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.144806261013059,
"count": 18191,
"is_parallel": true,
"self": 6.144806261013059
},
"communicator.exchange": {
"total": 179.15518822300396,
"count": 18191,
"is_parallel": true,
"self": 179.15518822300396
},
"steps_from_proto": {
"total": 36.148939981009676,
"count": 18191,
"is_parallel": true,
"self": 6.621626836979317,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.52731314403036,
"count": 181910,
"is_parallel": true,
"self": 29.52731314403036
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 127.22782333199143,
"count": 18192,
"self": 0.5248508080005649,
"children": {
"process_trajectory": {
"total": 28.17028037799014,
"count": 18192,
"self": 27.707328260990266,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4629521169998725,
"count": 4,
"self": 0.4629521169998725
}
}
},
"_update_policy": {
"total": 98.53269214600073,
"count": 90,
"self": 40.32258928199735,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.210102864003375,
"count": 4587,
"self": 58.210102864003375
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3910000689065782e-06,
"count": 1,
"self": 1.3910000689065782e-06
},
"TrainerController._save_models": {
"total": 0.1376931519998834,
"count": 1,
"self": 0.0011857989998134144,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13650735300007,
"count": 1,
"self": 0.13650735300007
}
}
}
}
}
}
}