{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001978111,0.0009528892,0.0013646,0.0005081122,0.0003401289,0.0009354696,0.001005531,0.001044723,0.002396285],"category_scores_gemma":[0.004938869,0.0006939853,0.0007062279,0.0003934334,0.0009863738,0.0008519637,0.001015504,0.001676879,0.0003138665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001371735,"about_ca_system_score_gemma":0.002019288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007205281,"about_ca_topic_score_gemma":0.006554819,"domain_scores_codex":[0.99932,0.000272192,0.00002688894,0.0001349045,0.0001361154,0.0001098213],"domain_scores_gemma":[0.9972759,0.001984588,0.0002012724,0.00007439037,0.0003593455,0.0001044614],"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":[0.00003609817,0.0000245719,0.0002090797,0.0000223726,0.00001364473,0.00001213423,0.00001304139,0.9881467,0.0003568297,0.002796141,0.0001553589,0.008213997],"study_design_scores_gemma":[0.000002912057,0.000007006773,0.00001549657,0.000001452976,0.00000140906,6.410175e-7,8.816067e-7,0.9992241,0.00005651071,0.0006623765,0.00002624939,8.744532e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02380617,0.0001799119,0.9737998,0.0002538527,0.00002482013,0.00005378694,0.00003828518,0.0002677327,0.001575736],"genre_scores_gemma":[0.9059222,0.0001285069,0.09140905,0.0001741783,0.00002517916,0.0002221183,0.0001164605,0.00006981475,0.001932482],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007205281,"threshold_uncertainty_score":0.01432669,"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."}}