{"id":"W4413167520","doi":"10.1016/j.ifacol.2025.07.153","title":"A Reinforcement Learning Approach for Simultaneous Generation, Design and Control of Reaction-Separation Process Flowsheets","year":2025,"lang":"en","type":"article","venue":"IFAC-PapersOnLine","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Process (computing); Control (management); Reinforcement; Process engineering; Separation (statistics); Computer science; Biochemical engineering; Artificial intelligence; Engineering; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.0001679478,0.0001515309,0.0002348884,0.00009534383,0.00009779117,0.00002191141,0.00005244281,0.00009110516,0.000001707103],"category_scores_gemma":[0.0002089533,0.000154605,0.00003288614,0.0001421293,0.00001661887,0.000167874,0.000004399175,0.0000834516,4.424656e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006880315,"about_ca_system_score_gemma":0.00002965726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003984565,"about_ca_topic_score_gemma":0.000003027152,"domain_scores_codex":[0.999169,0.00003079318,0.0003488882,0.0001907859,0.0001075387,0.0001530097],"domain_scores_gemma":[0.999408,0.000159937,0.00008944963,0.0001060635,0.0002043318,0.00003219279],"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":[0.00007068945,0.00001285533,0.00001494865,0.0001694323,0.00006520379,2.364836e-7,0.0002151868,0.8907986,0.1046002,0.00008789887,0.000001719461,0.003963066],"study_design_scores_gemma":[0.001603154,0.00007747162,0.000005858896,0.00003271979,0.00005357617,0.000002154927,0.0001025095,0.9924076,0.005465277,0.00001610606,0.0001068062,0.0001267281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00482828,0.0004293294,0.9928405,0.00004639913,0.0001017996,0.00123902,0.00000524487,0.0001471796,0.0003622556],"genre_scores_gemma":[0.7792071,0.00003604929,0.2200589,0.00003017401,0.00007742477,0.000228655,0.0001073996,0.00001961811,0.0002346472],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7743788,"threshold_uncertainty_score":0.6304607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009716572924903992,"score_gpt":0.2526142833833547,"score_spread":0.2428977104584507,"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."}}