{"id":"W4414861064","doi":"10.1093/jcde/qwaf100","title":"Optimizing Markov decision process state design for deep reinforcement learning manufacturing scheduling using Bayesian optimization","year":2025,"lang":"en","type":"article","venue":"Journal of Computational Design and Engineering","topic":"Manufacturing Process and Optimization","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"Incheon National University","keywords":"Reinforcement learning; Markov decision process; Scheduling (production processes); Job shop scheduling; Dynamic priority scheduling; Bayesian optimization; Feature selection; Partially observable Markov decision process","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":[],"consensus_categories":[],"category_scores_codex":[0.0005517954,0.0002262783,0.0002825204,0.0005145445,0.0001711063,0.0001734442,0.0001163923,0.00007786795,0.000006206312],"category_scores_gemma":[0.00009438262,0.0002335654,0.00006682209,0.0001740698,0.00001069473,0.0004740702,0.00001929193,0.0002276329,1.269057e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001326318,"about_ca_system_score_gemma":0.00006337168,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.212722e-7,"about_ca_topic_score_gemma":3.833919e-8,"domain_scores_codex":[0.9987321,0.00002344484,0.0006153631,0.0001474549,0.000233792,0.0002478382],"domain_scores_gemma":[0.9990416,0.0004292851,0.0001706155,0.00005222241,0.0002164431,0.00008985686],"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":[0.0001008471,0.000006959346,0.000004603923,0.0003577117,0.00009082073,0.000004070233,0.0002478017,0.991365,0.0001344496,0.00001453404,0.000004993287,0.007668205],"study_design_scores_gemma":[0.0008005261,0.00006381303,0.00002969727,0.0005315577,0.00005371706,0.00002503935,0.00004306616,0.9921489,0.005292097,0.0007778994,0.00001902726,0.0002146142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00970579,0.0005928791,0.9890018,0.00001337704,0.0002923376,0.0002919931,2.916928e-7,0.00008712472,0.00001442711],"genre_scores_gemma":[0.4713503,0.00009317391,0.5284729,0.000008621293,0.00003584061,0.000006030664,0.000002826072,0.00002511255,0.000005191792],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4616445,"threshold_uncertainty_score":0.9524519,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01109700207048009,"score_gpt":0.2358760649696818,"score_spread":0.2247790628992017,"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."}}