{"id":"W4415427665","doi":"10.3233/faia251421","title":"Learning an Efficient Optimizer via Hybrid-Policy Sub-Trajectory Balance","year":2025,"lang":"en","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Transportation and Mobility Innovations","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; China Scholarship Council; National Natural Science Foundation of China; Danmarks Grundforskningsfond","keywords":"Flexibility (engineering); Inefficiency; Inference; Artificial neural network; Limiting; Domain (mathematical analysis); Optimization problem","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000119853,0.0002558676,0.0002782934,0.0004975826,0.0001472623,0.00004636965,0.0001794862,0.0001758206,0.00003992659],"category_scores_gemma":[0.000009465469,0.0003152349,0.000062425,0.0002262888,0.0001701165,0.0000638208,0.00001330207,0.0005040511,0.00002632865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001234715,"about_ca_system_score_gemma":0.00008142307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001957412,"about_ca_topic_score_gemma":0.00005510463,"domain_scores_codex":[0.9987285,0.000009354002,0.0005397823,0.0003751795,0.0001246678,0.0002224856],"domain_scores_gemma":[0.9994329,0.00003401006,0.0000649317,0.0003023198,0.00008316788,0.00008272619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009674763,0.00006119032,0.00008065494,0.00009804749,0.00004679191,0.000002174653,0.0003005176,0.4640624,0.0001863016,0.2607276,0.0008101075,0.2736145],"study_design_scores_gemma":[0.0001023439,0.00006867016,0.0002376943,0.0002610844,0.0001279401,0.000004481694,0.0007476154,0.6731489,0.004623392,0.1261152,0.1932018,0.001360911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004715553,0.0005535852,0.9514971,0.00009177809,0.0002960665,0.0006845007,0.00009067937,0.0002779339,0.04603682],"genre_scores_gemma":[0.906567,0.007045461,0.03341638,0.0005350219,0.001301235,0.002067657,0.002249586,0.0003002427,0.04651742],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9180807,"threshold_uncertainty_score":0.99993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01453050269501096,"score_gpt":0.2480937704820477,"score_spread":0.2335632677870368,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}