{"id":"W4411871936","doi":"10.1016/j.compchemeng.2025.109249","title":"Computing control invariant set using reinforcement learning by leveraging default value function","year":2025,"lang":"en","type":"article","venue":"Computers & Chemical Engineering","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Reinforcement learning; Invariant (physics); Bellman equation; Function (biology); Computer science; Value (mathematics); Set (abstract data type); Control (management); Artificial intelligence; Mathematics; Mathematical optimization; Machine learning; Biology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001862517,0.0009724114,0.001337118,0.00095002,0.0003991092,0.001136507,0.001432132,0.0009728507,0.001961648],"category_scores_gemma":[0.006396064,0.0004884353,0.0007359466,0.0004220943,0.001893379,0.001529955,0.001549264,0.001833424,0.000283737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001384728,"about_ca_system_score_gemma":0.001496785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004550883,"about_ca_topic_score_gemma":0.003294476,"domain_scores_codex":[0.9993531,0.0001655364,0.0000377724,0.0001864464,0.0001729506,0.00008411673],"domain_scores_gemma":[0.9977328,0.001439668,0.0002813277,0.0002114622,0.0002286149,0.0001062324],"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":[0.00004427916,0.00002175228,0.0006251245,0.00002942621,0.00002182095,0.00004558702,0.00002775547,0.9653509,0.001013961,0.0127593,0.0002445373,0.01981547],"study_design_scores_gemma":[0.000002557963,0.00001028653,0.00003006175,0.000002470963,0.000001372603,0.00000316619,0.000001311021,0.9949729,0.0002235538,0.004700894,0.00004900307,0.000002328514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01179376,0.00006112061,0.9870811,0.00004772934,0.0000112348,0.00002290987,0.00002289111,0.0003508023,0.0006083901],"genre_scores_gemma":[0.8407989,0.000094135,0.1575814,0.00009143825,0.00002340525,0.0001474826,0.0001359853,0.0001270228,0.001000254],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004550883,"threshold_uncertainty_score":0.01004702,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004840853838555068,"score_gpt":0.1922002291779868,"score_spread":0.1873593753394318,"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."}}