{"id":"W4412569800","doi":"10.1016/j.jai.2025.07.001","title":"Novel multi-agent action masked deep reinforcement learning for general industrial assembly lines balancing problems","year":2025,"lang":"en","type":"article","venue":"Journal of Automation and Intelligence","topic":"Assembly Line Balancing Optimization","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Reinforcement; Action (physics); Computer science; Artificial intelligence; Psychology; Social psychology; Physics","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":[0.0003883622,0.0001197622,0.0001844644,0.0002335812,0.00009199006,0.00007842411,0.00007774865,0.0001028277,0.000006592027],"category_scores_gemma":[0.0002966725,0.0001129102,0.00005718712,0.0001934693,0.00001000311,0.0003436023,0.00001584227,0.0002014587,0.000001215499],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001463738,"about_ca_system_score_gemma":0.00004862447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005898162,"about_ca_topic_score_gemma":0.000008380732,"domain_scores_codex":[0.9989999,0.00001792163,0.0006122015,0.00008791561,0.0001438802,0.0001381692],"domain_scores_gemma":[0.9993141,0.00007113889,0.0002559227,0.00005707912,0.0002556434,0.00004612934],"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":[0.00001542384,0.0000158417,0.0002403428,0.0001027266,0.00004065389,2.183825e-7,0.0002452036,0.9430642,0.0271499,0.0001808934,0.0001229412,0.02882169],"study_design_scores_gemma":[0.0004438185,0.00008893757,0.000858795,0.0002503018,0.00003153083,0.00001090851,0.000176075,0.9723371,0.02448601,0.00002370333,0.001194188,0.00009869282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04688828,0.0001256221,0.9516121,0.00009689098,0.0008828604,0.0002312561,3.051481e-7,0.00007923872,0.00008347289],"genre_scores_gemma":[0.9456118,0.0003022165,0.0535015,0.00003823787,0.000253568,0.00001262031,0.000009706677,0.00001615823,0.0002542082],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8987235,"threshold_uncertainty_score":0.4604343,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04231911180534331,"score_gpt":0.295925254166449,"score_spread":0.2536061423611057,"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."}}