meanjai's picture
First Push
5c077c9 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8608944416046143,
"min": 0.853240966796875,
"max": 2.835796356201172,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8181.94091796875,
"min": 8181.94091796875,
"max": 28947.80859375,
"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": 12.986773490905762,
"min": 0.37495091557502747,
"max": 12.986773490905762,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2532.4208984375,
"min": 72.740478515625,
"max": 2648.263671875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06988301199774416,
"min": 0.06332955162325365,
"max": 0.07402194710037506,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27953204799097664,
"min": 0.2533182064930146,
"max": 0.3701097355018753,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18250421668384592,
"min": 0.14311674505691316,
"max": 0.2961836160397997,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7300168667353837,
"min": 0.5724669802276526,
"max": 1.4809180801989985,
"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": 25.886363636363637,
"min": 4.068181818181818,
"max": 26.227272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1139.0,
"min": 179.0,
"max": 1389.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.886363636363637,
"min": 4.068181818181818,
"max": 26.227272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1139.0,
"min": 179.0,
"max": 1389.0,
"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": "1750221812",
"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": "1750222294"
},
"total": 482.36612240800014,
"count": 1,
"self": 0.7002983200002291,
"children": {
"run_training.setup": {
"total": 0.03483153499996661,
"count": 1,
"self": 0.03483153499996661
},
"TrainerController.start_learning": {
"total": 481.63099255299994,
"count": 1,
"self": 0.42138732700777837,
"children": {
"TrainerController._reset_env": {
"total": 3.3593653589998667,
"count": 1,
"self": 3.3593653589998667
},
"TrainerController.advance": {
"total": 477.70779223699196,
"count": 18192,
"self": 0.47073473100044794,
"children": {
"env_step": {
"total": 348.08054050997,
"count": 18192,
"self": 268.3812043439593,
"children": {
"SubprocessEnvManager._take_step": {
"total": 79.44551369301507,
"count": 18192,
"self": 1.446065159005002,
"children": {
"TorchPolicy.evaluate": {
"total": 77.99944853401007,
"count": 18192,
"self": 77.99944853401007
}
}
},
"workers": {
"total": 0.25382247299558003,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 479.81929353299734,
"count": 18192,
"is_parallel": true,
"self": 244.68784028799405,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0051917669998147176,
"count": 1,
"is_parallel": true,
"self": 0.0036014139996041195,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015903530002105981,
"count": 10,
"is_parallel": true,
"self": 0.0015903530002105981
}
}
},
"UnityEnvironment.step": {
"total": 0.039994474999957674,
"count": 1,
"is_parallel": true,
"self": 0.0006958289998237888,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004550720000224828,
"count": 1,
"is_parallel": true,
"self": 0.0004550720000224828
},
"communicator.exchange": {
"total": 0.03679887599992071,
"count": 1,
"is_parallel": true,
"self": 0.03679887599992071
},
"steps_from_proto": {
"total": 0.0020446980001906923,
"count": 1,
"is_parallel": true,
"self": 0.0004145940001762938,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016301040000143985,
"count": 10,
"is_parallel": true,
"self": 0.0016301040000143985
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 235.13145324500329,
"count": 18191,
"is_parallel": true,
"self": 10.886901564983418,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.15488438199327,
"count": 18191,
"is_parallel": true,
"self": 6.15488438199327
},
"communicator.exchange": {
"total": 181.54548096502685,
"count": 18191,
"is_parallel": true,
"self": 181.54548096502685
},
"steps_from_proto": {
"total": 36.54418633299974,
"count": 18191,
"is_parallel": true,
"self": 6.655723821053925,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.888462511945818,
"count": 181910,
"is_parallel": true,
"self": 29.888462511945818
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 129.15651699602154,
"count": 18192,
"self": 0.5505249980292319,
"children": {
"process_trajectory": {
"total": 29.167751575992497,
"count": 18192,
"self": 28.745382072992015,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4223695030004819,
"count": 4,
"self": 0.4223695030004819
}
}
},
"_update_policy": {
"total": 99.43824042199981,
"count": 90,
"self": 41.40727959500532,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.03096082699449,
"count": 4587,
"self": 58.03096082699449
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1170000107085798e-06,
"count": 1,
"self": 1.1170000107085798e-06
},
"TrainerController._save_models": {
"total": 0.14244651300032274,
"count": 1,
"self": 0.0012108380001336627,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14123567500018908,
"count": 1,
"self": 0.14123567500018908
}
}
}
}
}
}
}