{"id":"W4411163025","doi":"10.1016/j.cor.2025.107159","title":"Random-Key Optimizer with reinforcement learning for the Capacitated Multi-period Cutting Stock Problem with setup cost","year":2025,"lang":"en","type":"article","venue":"Computers & Operations Research","topic":"Optimization and Packing Problems","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"HEC Montréal; Group for Research in Decision Analysis","funders":"Mitacs; Conselho Nacional de Desenvolvimento Científico e Tecnológico; HEC Montréal; Fundação de Amparo à Pesquisa do Estado de São Paulo; Healthcare Excellence Canada","keywords":"Reinforcement learning; Computer science; Key (lock); Mathematical optimization; Stock (firearms); Period (music); Reinforcement; Artificial intelligence; Operations research; Mathematics; Mechanical engineering; Engineering; Structural engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0007760312,0.0001806028,0.0001881384,0.000257323,0.001270905,0.0005953112,0.000274091,0.0000592332,0.00003467446],"category_scores_gemma":[0.00005993982,0.0001197476,0.00003676164,0.0008198611,0.0001372083,0.0001954311,0.00006303366,0.0005222335,0.000009777376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001349382,"about_ca_system_score_gemma":0.0001644096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005605976,"about_ca_topic_score_gemma":0.0001177285,"domain_scores_codex":[0.9986021,0.0001308014,0.0002672579,0.000253944,0.0002959885,0.0004499172],"domain_scores_gemma":[0.9986593,0.0003680472,0.00001649857,0.000284158,0.0005987042,0.00007334944],"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":[0.00009948502,0.00001997481,0.00008488811,0.00008048517,0.0001615299,0.000001497007,0.002353588,0.9922338,0.0001113913,0.0005009873,0.001854905,0.002497502],"study_design_scores_gemma":[0.003592591,0.0001414709,0.00002278245,0.0002311604,0.00001904052,0.00000499988,0.0005323481,0.9847613,0.0002989401,0.000001584023,0.01023616,0.0001576449],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008568044,0.0001304017,0.993119,0.0009476778,0.0001051862,0.002846382,0.000003542074,0.0002209836,0.001769994],"genre_scores_gemma":[0.6474387,0.0001057292,0.3425508,0.0001252761,0.00006296658,0.002078041,0.0001745982,0.00007964702,0.007384174],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6505682,"threshold_uncertainty_score":0.9774904,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04743423773720279,"score_gpt":0.3228343211424024,"score_spread":0.2754000834051996,"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."}}