{"id":"W4402067153","doi":"10.1002/aic.18584","title":"A reinforcement learning approach with masked agents for chemical process flowsheet design","year":2024,"lang":"en","type":"article","venue":"AIChE Journal","topic":"Scheduling and Optimization Algorithms","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Process (computing); Reinforcement; Process engineering; Computer science; Biochemical engineering; Engineering; Materials science; Artificial intelligence; Composite material; Programming language","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":[0.0002944009,0.0001241108,0.0001131134,0.00008129427,0.00008259094,0.0001878377,0.0001059493,0.00006208209,0.00005167827],"category_scores_gemma":[0.00003576372,0.00009628475,0.00004725737,0.0001814314,0.00001152375,0.0001392244,0.000006611577,0.000368909,0.00000846737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006478144,"about_ca_system_score_gemma":0.00005240037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":1.789174e-7,"about_ca_topic_score_gemma":1.887983e-8,"domain_scores_codex":[0.9992757,0.00001324066,0.0001825627,0.0001124793,0.0001933416,0.0002227105],"domain_scores_gemma":[0.9997148,0.00003710631,0.00002233764,0.00005931007,0.0000649182,0.0001015484],"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":[0.00002529377,0.000007938615,0.000008744689,0.0001084207,0.0001010241,0.000007705274,0.000865481,0.9955636,0.0002434854,0.00002365479,0.0009093721,0.002135325],"study_design_scores_gemma":[0.0004394521,0.00006398962,0.000001999357,0.00009682179,0.00004374937,0.0001565808,0.0002271723,0.9949711,0.00274913,0.00004482937,0.001063261,0.0001418911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005323037,0.0002720682,0.9926091,0.00004324207,0.0001974993,0.0001605683,4.820311e-7,0.0002516745,0.001142351],"genre_scores_gemma":[0.6037311,0.00005130156,0.3949427,0.00004117666,0.0004099445,0.0000576852,0.00001639677,0.00006688544,0.0006827958],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5984081,"threshold_uncertainty_score":0.3926378,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02193525708122232,"score_gpt":0.2493957199066536,"score_spread":0.2274604628254313,"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."}}