mejdi86's picture
First Push
8e13486 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9849469661712646,
"min": 0.9849469661712646,
"max": 2.8772785663604736,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9404.2734375,
"min": 9404.2734375,
"max": 29466.208984375,
"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": 12.180524826049805,
"min": 0.37483397126197815,
"max": 12.22553825378418,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2375.202392578125,
"min": 72.71778869628906,
"max": 2494.009765625,
"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": 0.06868359489525057,
"min": 0.062364463874723254,
"max": 0.07434767477902557,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2747343795810023,
"min": 0.2556851053605879,
"max": 0.3587016153478009,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.243040766420902,
"min": 0.11568850047849849,
"max": 0.28026491469320125,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.972163065683608,
"min": 0.46275400191399396,
"max": 1.3992151650143605,
"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": 23.75,
"min": 3.3636363636363638,
"max": 24.490909090909092,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1045.0,
"min": 148.0,
"max": 1347.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.75,
"min": 3.3636363636363638,
"max": 24.490909090909092,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1045.0,
"min": 148.0,
"max": 1347.0,
"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": "1717927854",
"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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1717928328"
},
"total": 474.2017830550003,
"count": 1,
"self": 0.4354397410002093,
"children": {
"run_training.setup": {
"total": 0.05575185799989413,
"count": 1,
"self": 0.05575185799989413
},
"TrainerController.start_learning": {
"total": 473.7105914560002,
"count": 1,
"self": 0.6117639550429885,
"children": {
"TrainerController._reset_env": {
"total": 3.5179187110002204,
"count": 1,
"self": 3.5179187110002204
},
"TrainerController.advance": {
"total": 469.49020842295704,
"count": 18202,
"self": 0.2973918569550733,
"children": {
"env_step": {
"total": 469.19281656600197,
"count": 18202,
"self": 306.9053457759687,
"children": {
"SubprocessEnvManager._take_step": {
"total": 161.9762788390476,
"count": 18202,
"self": 1.5761180820391019,
"children": {
"TorchPolicy.evaluate": {
"total": 160.4001607570085,
"count": 18202,
"self": 160.4001607570085
}
}
},
"workers": {
"total": 0.3111919509856307,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 472.42562163903176,
"count": 18202,
"is_parallel": true,
"self": 237.99273284102992,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006315120000181196,
"count": 1,
"is_parallel": true,
"self": 0.003980104000675055,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023350159995061404,
"count": 10,
"is_parallel": true,
"self": 0.0023350159995061404
}
}
},
"UnityEnvironment.step": {
"total": 0.04321080499994423,
"count": 1,
"is_parallel": true,
"self": 0.0007072469998092856,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004017370001747622,
"count": 1,
"is_parallel": true,
"self": 0.0004017370001747622
},
"communicator.exchange": {
"total": 0.039867937000053644,
"count": 1,
"is_parallel": true,
"self": 0.039867937000053644
},
"steps_from_proto": {
"total": 0.0022338839999065385,
"count": 1,
"is_parallel": true,
"self": 0.0003966559993386909,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018372280005678476,
"count": 10,
"is_parallel": true,
"self": 0.0018372280005678476
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 234.43288879800184,
"count": 18201,
"is_parallel": true,
"self": 10.598687655981848,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.604765089988632,
"count": 18201,
"is_parallel": true,
"self": 5.604765089988632
},
"communicator.exchange": {
"total": 182.7245893150125,
"count": 18201,
"is_parallel": true,
"self": 182.7245893150125
},
"steps_from_proto": {
"total": 35.50484673701885,
"count": 18201,
"is_parallel": true,
"self": 6.797648236042733,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.70719850097612,
"count": 182010,
"is_parallel": true,
"self": 28.70719850097612
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014005899993208004,
"count": 1,
"self": 0.00014005899993208004,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 463.82534294820243,
"count": 692690,
"is_parallel": true,
"self": 14.739681255443884,
"children": {
"process_trajectory": {
"total": 256.7566493927543,
"count": 692690,
"is_parallel": true,
"self": 255.79934155475394,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9573078380003608,
"count": 4,
"is_parallel": true,
"self": 0.9573078380003608
}
}
},
"_update_policy": {
"total": 192.32901230000425,
"count": 90,
"is_parallel": true,
"self": 62.943292347994884,
"children": {
"TorchPPOOptimizer.update": {
"total": 129.38571995200937,
"count": 4587,
"is_parallel": true,
"self": 129.38571995200937
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0905603080000219,
"count": 1,
"self": 0.001023581000026752,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08953672699999515,
"count": 1,
"self": 0.08953672699999515
}
}
}
}
}
}
}