{"id":"W4411745897","doi":"10.1007/978-3-031-95973-8_15","title":"Bounded-Error Policy Optimization for Mixed Discrete-Continuous MDPs via Constraint Generation in Nonlinear Programming","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Auction Theory and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Bounded function; Nonlinear programming; Constraint (computer-aided design); Mathematical optimization; Nonlinear system; Constraint satisfaction; Mathematics; Artificial intelligence","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":[0.002479496,0.0003496083,0.0004927624,0.001414214,0.0004411366,0.0007648662,0.001231661,0.000316764,0.0000619873],"category_scores_gemma":[0.001229766,0.0003007061,0.0001558945,0.00128826,0.0008988344,0.0003942776,0.0002878903,0.0003957443,0.00001387443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002919781,"about_ca_system_score_gemma":0.0008113111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002697535,"about_ca_topic_score_gemma":0.0003613638,"domain_scores_codex":[0.9963673,0.00007294658,0.0009827645,0.00130508,0.0008295421,0.0004424036],"domain_scores_gemma":[0.9973144,0.0007524949,0.0004831153,0.0007807021,0.0005618274,0.0001074541],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001006536,0.00002569821,0.00001047489,0.000007655435,0.000003210255,0.000001826985,0.0003221328,0.3032531,0.00006244236,0.02681828,0.00003218363,0.6694529],"study_design_scores_gemma":[0.0002505089,0.00006381855,0.000007958273,0.00007012267,0.000007278144,0.0000114702,0.000003826296,0.8071834,0.0004620593,0.1853956,0.006265059,0.0002788815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001891678,0.00005357444,0.9946598,0.002023041,0.0007630398,0.001243277,0.00004314459,0.0000569246,0.000968022],"genre_scores_gemma":[0.1134901,0.00001010563,0.8823475,0.0008528407,0.001141447,0.0001462485,0.0001146174,0.00002922571,0.001867911],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.669174,"threshold_uncertainty_score":0.9999445,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04396380494695325,"score_gpt":0.3500265044534952,"score_spread":0.306062699506542,"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."}}