r0in's picture
First Push
bd3ed9d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7549917697906494,
"min": 0.7549917697906494,
"max": 2.8673477172851562,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7208.66162109375,
"min": 7208.66162109375,
"max": 29364.5078125,
"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": 13.019375801086426,
"min": 0.30637022852897644,
"max": 13.019375801086426,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2538.7783203125,
"min": 59.435821533203125,
"max": 2644.74267578125,
"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.Losses.PolicyLoss.mean": {
"value": 0.06869654145845619,
"min": 0.06383492239979474,
"max": 0.07363710567191376,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27478616583382476,
"min": 0.2651702601111074,
"max": 0.3665418383471643,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19557429769752074,
"min": 0.1145789120951211,
"max": 0.2985586024382535,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.782297190790083,
"min": 0.4583156483804844,
"max": 1.406102462434301,
"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.CumulativeReward.mean": {
"value": 25.545454545454547,
"min": 3.3863636363636362,
"max": 25.945454545454545,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1124.0,
"min": 149.0,
"max": 1427.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.545454545454547,
"min": 3.3863636363636362,
"max": 25.945454545454545,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1124.0,
"min": 149.0,
"max": 1427.0,
"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": "1707187724",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1707188213"
},
"total": 489.34237432,
"count": 1,
"self": 0.43621158299981744,
"children": {
"run_training.setup": {
"total": 0.05159399200010739,
"count": 1,
"self": 0.05159399200010739
},
"TrainerController.start_learning": {
"total": 488.85456874500005,
"count": 1,
"self": 0.6863259479997623,
"children": {
"TrainerController._reset_env": {
"total": 3.453969723,
"count": 1,
"self": 3.453969723
},
"TrainerController.advance": {
"total": 484.6098857630003,
"count": 18199,
"self": 0.36020145699069417,
"children": {
"env_step": {
"total": 484.2496843060096,
"count": 18199,
"self": 315.0260710820038,
"children": {
"SubprocessEnvManager._take_step": {
"total": 168.8869209759946,
"count": 18199,
"self": 1.6871988759916121,
"children": {
"TorchPolicy.evaluate": {
"total": 167.199722100003,
"count": 18199,
"self": 167.199722100003
}
}
},
"workers": {
"total": 0.336692248011218,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 487.41727095699866,
"count": 18199,
"is_parallel": true,
"self": 240.80303587700212,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0047078249999685795,
"count": 1,
"is_parallel": true,
"self": 0.003077184999824567,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016306400001440124,
"count": 10,
"is_parallel": true,
"self": 0.0016306400001440124
}
}
},
"UnityEnvironment.step": {
"total": 0.040488466999931916,
"count": 1,
"is_parallel": true,
"self": 0.0006993059998876561,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004289030000563798,
"count": 1,
"is_parallel": true,
"self": 0.0004289030000563798
},
"communicator.exchange": {
"total": 0.03716246900000897,
"count": 1,
"is_parallel": true,
"self": 0.03716246900000897
},
"steps_from_proto": {
"total": 0.0021977889999789113,
"count": 1,
"is_parallel": true,
"self": 0.0004284289998395252,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001769360000139386,
"count": 10,
"is_parallel": true,
"self": 0.001769360000139386
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 246.61423507999655,
"count": 18198,
"is_parallel": true,
"self": 11.475560995007754,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.964535762989954,
"count": 18198,
"is_parallel": true,
"self": 5.964535762989954
},
"communicator.exchange": {
"total": 191.69741891999956,
"count": 18198,
"is_parallel": true,
"self": 191.69741891999956
},
"steps_from_proto": {
"total": 37.476719401999276,
"count": 18198,
"is_parallel": true,
"self": 7.245893346028879,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.230826055970397,
"count": 181980,
"is_parallel": true,
"self": 30.230826055970397
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011941499997192295,
"count": 1,
"self": 0.00011941499997192295,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 478.4372463459259,
"count": 730667,
"is_parallel": true,
"self": 16.3003039018937,
"children": {
"process_trajectory": {
"total": 265.7993463050327,
"count": 730667,
"is_parallel": true,
"self": 264.9483256450326,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8510206600001311,
"count": 4,
"is_parallel": true,
"self": 0.8510206600001311
}
}
},
"_update_policy": {
"total": 196.33759613899952,
"count": 90,
"is_parallel": true,
"self": 53.20181608500286,
"children": {
"TorchPPOOptimizer.update": {
"total": 143.13578005399665,
"count": 4587,
"is_parallel": true,
"self": 143.13578005399665
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1042678960000103,
"count": 1,
"self": 0.0013942260000021633,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10287367000000813,
"count": 1,
"self": 0.10287367000000813
}
}
}
}
}
}
}