Paulcvbg's picture
First Push
aaba1f9 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8945086598396301,
"min": 0.8738523125648499,
"max": 2.860318183898926,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8501.41015625,
"min": 8439.7197265625,
"max": 29198.126953125,
"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": 12.980091094970703,
"min": 0.30573928356170654,
"max": 12.980091094970703,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2531.11767578125,
"min": 59.31342315673828,
"max": 2631.7548828125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07337112193250933,
"min": 0.06064589252313382,
"max": 0.07692390735842221,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2934844877300373,
"min": 0.24258357009253528,
"max": 0.384619536792111,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21164298229211687,
"min": 0.09529717052218449,
"max": 0.30087320827970315,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8465719291684675,
"min": 0.38118868208873796,
"max": 1.5043660413985158,
"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": 26.204545454545453,
"min": 2.7954545454545454,
"max": 26.204545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1153.0,
"min": 123.0,
"max": 1412.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.204545454545453,
"min": 2.7954545454545454,
"max": 26.204545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1153.0,
"min": 123.0,
"max": 1412.0,
"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": "1743954205",
"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": "1743954650"
},
"total": 445.20348389700007,
"count": 1,
"self": 0.43375170000012986,
"children": {
"run_training.setup": {
"total": 0.023421772000006058,
"count": 1,
"self": 0.023421772000006058
},
"TrainerController.start_learning": {
"total": 444.74631042499993,
"count": 1,
"self": 0.3515316479986268,
"children": {
"TrainerController._reset_env": {
"total": 3.259395037000104,
"count": 1,
"self": 3.259395037000104
},
"TrainerController.advance": {
"total": 441.04100375500104,
"count": 18192,
"self": 0.36878996400389497,
"children": {
"env_step": {
"total": 311.00540443699936,
"count": 18192,
"self": 237.8346939370058,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.95216803500216,
"count": 18192,
"self": 1.2874210039997251,
"children": {
"TorchPolicy.evaluate": {
"total": 71.66474703100243,
"count": 18192,
"self": 71.66474703100243
}
}
},
"workers": {
"total": 0.21854246499140118,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 443.25033389401506,
"count": 18192,
"is_parallel": true,
"self": 234.02664343001902,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007242239999982303,
"count": 1,
"is_parallel": true,
"self": 0.0047525049998284885,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024897350001538143,
"count": 10,
"is_parallel": true,
"self": 0.0024897350001538143
}
}
},
"UnityEnvironment.step": {
"total": 0.04244667800003299,
"count": 1,
"is_parallel": true,
"self": 0.0006555669999670499,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003966710000895546,
"count": 1,
"is_parallel": true,
"self": 0.0003966710000895546
},
"communicator.exchange": {
"total": 0.03903722799998377,
"count": 1,
"is_parallel": true,
"self": 0.03903722799998377
},
"steps_from_proto": {
"total": 0.0023572119999926144,
"count": 1,
"is_parallel": true,
"self": 0.0004334910000807213,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019237209999118932,
"count": 10,
"is_parallel": true,
"self": 0.0019237209999118932
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 209.22369046399604,
"count": 18191,
"is_parallel": true,
"self": 10.114902355992058,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.446227257998771,
"count": 18191,
"is_parallel": true,
"self": 5.446227257998771
},
"communicator.exchange": {
"total": 161.2884265100032,
"count": 18191,
"is_parallel": true,
"self": 161.2884265100032
},
"steps_from_proto": {
"total": 32.374134340002,
"count": 18191,
"is_parallel": true,
"self": 5.680987043991308,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.693147296010693,
"count": 181910,
"is_parallel": true,
"self": 26.693147296010693
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 129.6668093539978,
"count": 18192,
"self": 0.43123829800754265,
"children": {
"process_trajectory": {
"total": 28.205224656989685,
"count": 18192,
"self": 27.7578929199899,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4473317369997858,
"count": 4,
"self": 0.4473317369997858
}
}
},
"_update_policy": {
"total": 101.03034639900056,
"count": 90,
"self": 41.12142111400124,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.90892528499933,
"count": 4587,
"self": 59.90892528499933
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.96000153463683e-07,
"count": 1,
"self": 9.96000153463683e-07
},
"TrainerController._save_models": {
"total": 0.09437898900000619,
"count": 1,
"self": 0.0010024810001141304,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09337650799989206,
"count": 1,
"self": 0.09337650799989206
}
}
}
}
}
}
}