{"id":"W4413167759","doi":"10.1016/j.ifacol.2025.07.155","title":"Hybrid Deep Reinforcement Learning Agent for Online Scheduling and Control for Chemical Batch Plants","year":2025,"lang":"en","type":"article","venue":"IFAC-PapersOnLine","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Consejo Nacional de Ciencia y Tecnología","keywords":"Reinforcement learning; Computer science; Scheduling (production processes); Control (management); 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"],"consensus_categories":[],"category_scores_codex":[0.0001467322,0.000246734,0.000384084,0.00009052982,0.0001125005,0.00003613443,0.0001076757,0.00009596387,0.000006414015],"category_scores_gemma":[0.0002410593,0.0002558724,0.00009079452,0.00006229774,0.00002124883,0.0001140746,0.00002311022,0.000163603,0.000001594906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001348806,"about_ca_system_score_gemma":0.00002119812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004499689,"about_ca_topic_score_gemma":0.000008651338,"domain_scores_codex":[0.9987811,0.00001259087,0.0004170201,0.0002914201,0.0001125128,0.0003853706],"domain_scores_gemma":[0.9993557,0.0002607765,0.00007303102,0.0001489701,0.0000860912,0.00007537998],"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":[0.0001728353,0.00002049457,0.00005628016,0.000282677,0.0001557018,0.000001184794,0.00007317074,0.9371787,0.04331673,0.0001380167,0.000006282064,0.01859788],"study_design_scores_gemma":[0.00453253,0.00006426768,0.00001806276,0.0001431463,0.00007395583,0.000004544759,0.0001178647,0.9890949,0.003708933,0.00008149111,0.001922624,0.0002376973],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.047485,0.001231556,0.9490135,0.0003051562,0.0003139126,0.001198314,0.00007822123,0.0002742782,0.000100024],"genre_scores_gemma":[0.6823455,0.0001232585,0.3158931,0.0002357471,0.000283853,0.0002642273,0.0004746244,0.00005251408,0.0003271495],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6348605,"threshold_uncertainty_score":0.9999893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007144667660866758,"score_gpt":0.2354553423166664,"score_spread":0.2283106746557996,"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."}}