{"id":"W4410826557","doi":"10.2139/ssrn.5272328","title":"Interpretable Online Scheduling for Chemical Batch Plants with Attention Augmented Reinforcement Learning Agents","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Scheduling (production processes); Reinforcement; Computer science; Artificial intelligence; Engineering; Operations management","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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0007809185,0.0003941027,0.0005218192,0.0002132554,0.0001337042,0.00009383211,0.0003256308,0.0002774126,0.000008377033],"category_scores_gemma":[0.00005968613,0.0003839548,0.0001934523,0.00009397668,0.00001525604,0.0001787668,0.0001156535,0.003611412,0.000002166149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002535293,"about_ca_system_score_gemma":0.000750894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001565693,"about_ca_topic_score_gemma":0.0000690695,"domain_scores_codex":[0.9969361,0.00005352986,0.0007547091,0.0003515532,0.0002826499,0.001621387],"domain_scores_gemma":[0.9991102,0.00004339252,0.0003670017,0.0002258661,0.0001684657,0.0000851337],"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":[0.0001791781,0.00002553923,0.0002315416,0.0001747098,0.001058944,0.000001073354,0.00005763129,0.9898238,0.00066458,0.0003353231,0.00002208206,0.007425628],"study_design_scores_gemma":[0.002165465,0.0001571875,0.00001362307,0.001366183,0.0001881199,0.0000555628,0.0004940807,0.9927731,0.0001495904,0.00182153,0.0004247518,0.0003907719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05776073,0.001530161,0.9385704,0.00004386845,0.0007442834,0.0007666016,0.00001629197,0.0002228796,0.0003447827],"genre_scores_gemma":[0.9857604,0.003549416,0.006826157,0.00001890445,0.0004870837,0.0001165822,0.0006156936,0.00008573011,0.002540043],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9317443,"threshold_uncertainty_score":0.9998612,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007054414651572988,"score_gpt":0.2409170626854051,"score_spread":0.2338626480338321,"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."}}