mblond's picture
First push of SnowballTarget model
36df0b0 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8057221174240112,
"min": 0.8057221174240112,
"max": 2.845973253250122,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7657.5830078125,
"min": 7657.5830078125,
"max": 29051.6953125,
"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": 12.730793952941895,
"min": 0.3926199972629547,
"max": 12.730793952941895,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2482.5048828125,
"min": 76.16828155517578,
"max": 2600.15087890625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06737306700408369,
"min": 0.06322753251776757,
"max": 0.0734850360267064,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26949226801633475,
"min": 0.2534655845169361,
"max": 0.35938620727763776,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19263010373448625,
"min": 0.14304609776602364,
"max": 0.2900649314417558,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.770520414937945,
"min": 0.5721843910640946,
"max": 1.4503246572087791,
"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": 24.977272727272727,
"min": 3.772727272727273,
"max": 25.30909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1099.0,
"min": 166.0,
"max": 1392.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.977272727272727,
"min": 3.772727272727273,
"max": 25.30909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1099.0,
"min": 166.0,
"max": 1392.0,
"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": "1750937309",
"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=SnowballTarget_mblond --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": "1750937727"
},
"total": 418.350743151,
"count": 1,
"self": 0.43128578800002515,
"children": {
"run_training.setup": {
"total": 0.022565985000028377,
"count": 1,
"self": 0.022565985000028377
},
"TrainerController.start_learning": {
"total": 417.89689137799996,
"count": 1,
"self": 0.330631888993139,
"children": {
"TrainerController._reset_env": {
"total": 3.047841312999992,
"count": 1,
"self": 3.047841312999992
},
"TrainerController.advance": {
"total": 414.43931139600676,
"count": 18192,
"self": 0.35842988101160245,
"children": {
"env_step": {
"total": 297.2398720959993,
"count": 18192,
"self": 228.21551760801253,
"children": {
"SubprocessEnvManager._take_step": {
"total": 68.82355495499183,
"count": 18192,
"self": 1.212500073991123,
"children": {
"TorchPolicy.evaluate": {
"total": 67.61105488100071,
"count": 18192,
"self": 67.61105488100071
}
}
},
"workers": {
"total": 0.20079953299494946,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 416.23769626300697,
"count": 18192,
"is_parallel": true,
"self": 215.82305643499876,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005510313000002043,
"count": 1,
"is_parallel": true,
"self": 0.004079289999936009,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001431023000066034,
"count": 10,
"is_parallel": true,
"self": 0.001431023000066034
}
}
},
"UnityEnvironment.step": {
"total": 0.03678357399996912,
"count": 1,
"is_parallel": true,
"self": 0.0006530389999284125,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004146500000388187,
"count": 1,
"is_parallel": true,
"self": 0.0004146500000388187
},
"communicator.exchange": {
"total": 0.03356288800000584,
"count": 1,
"is_parallel": true,
"self": 0.03356288800000584
},
"steps_from_proto": {
"total": 0.0021529969999960485,
"count": 1,
"is_parallel": true,
"self": 0.00043409699998164797,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017189000000144006,
"count": 10,
"is_parallel": true,
"self": 0.0017189000000144006
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 200.4146398280082,
"count": 18191,
"is_parallel": true,
"self": 9.648756043994638,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.306417594008053,
"count": 18191,
"is_parallel": true,
"self": 5.306417594008053
},
"communicator.exchange": {
"total": 154.37938147599766,
"count": 18191,
"is_parallel": true,
"self": 154.37938147599766
},
"steps_from_proto": {
"total": 31.080084714007853,
"count": 18191,
"is_parallel": true,
"self": 5.58018032799572,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.499904386012133,
"count": 181910,
"is_parallel": true,
"self": 25.499904386012133
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 116.84100941899584,
"count": 18192,
"self": 0.4049387699951694,
"children": {
"process_trajectory": {
"total": 25.7070339680011,
"count": 18192,
"self": 25.271641961000967,
"children": {
"RLTrainer._checkpoint": {
"total": 0.43539200700013225,
"count": 4,
"self": 0.43539200700013225
}
}
},
"_update_policy": {
"total": 90.72903668099957,
"count": 90,
"self": 37.18717793199562,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.54185874900395,
"count": 4587,
"self": 53.54185874900395
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.610000688553555e-07,
"count": 1,
"self": 9.610000688553555e-07
},
"TrainerController._save_models": {
"total": 0.0791058190000058,
"count": 1,
"self": 0.0008080929999323416,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07829772600007345,
"count": 1,
"self": 0.07829772600007345
}
}
}
}
}
}
}