{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006287334,0.000587199,0.0006298159,0.0001965957,0.0002842078,0.0005297213,0.001018499,0.0008108859,0.001923488],"category_scores_gemma":[0.0009696706,0.0002761126,0.0003679126,0.0001334747,0.0005271382,0.0004266883,0.0007355269,0.000966112,0.0002886373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007720289,"about_ca_system_score_gemma":0.001161081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007081607,"about_ca_topic_score_gemma":0.00638257,"domain_scores_codex":[0.9997616,0.00005608934,0.00001138659,0.00005156864,0.00007329242,0.00004593158],"domain_scores_gemma":[0.9996455,0.0001426001,0.00005162859,0.00002936072,0.00009776774,0.00003319941],"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":[0.00006485009,0.00005846761,0.0004671238,0.00003454425,0.00002603122,0.00005771931,0.0000276083,0.968282,0.002329722,0.003508643,0.0004929121,0.02465039],"study_design_scores_gemma":[0.000004102713,0.00001430257,0.00002560848,0.000001251856,0.000001559388,0.000003179514,0.000001049088,0.9992945,0.0002454498,0.0002718463,0.0001355662,0.000001439404],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04213658,0.0002415081,0.9515805,0.0002300477,0.00008606097,0.00006571482,0.00004989394,0.001073805,0.004535912],"genre_scores_gemma":[0.9153398,0.0000679678,0.08095355,0.0001105163,0.00002478936,0.0001170403,0.00005013839,0.00003227416,0.003303922],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007081607,"threshold_uncertainty_score":0.01408076,"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."}}