{"id":"W4412490456","doi":"10.1109/tcyb.2025.3579361","title":"EKG-AC: A New Paradigm for Process Industrial Optimization Based on Offline Reinforcement Learning With Expert Knowledge Guidance","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Energy Efficiency and Management","field":"Energy","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Hunan Provincial Innovation Foundation for Postgraduate; Natural Science Foundation of Hunan Province; National Natural Science Foundation of China","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Profitability index; Process (computing); Interdependence; Subject-matter expert; Machine learning; Adaptability; Domain knowledge; Expert system","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":[0.0001321139,0.000247294,0.0002034653,0.0002281966,0.0002574839,0.0000511033,0.0001876729,0.000142929,0.0001240765],"category_scores_gemma":[0.00002024396,0.0002265604,0.00008142614,0.0005238574,0.00004618491,0.00006995561,0.000001382524,0.0002310033,0.000007592455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001399281,"about_ca_system_score_gemma":0.0002602047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000161066,"about_ca_topic_score_gemma":0.0002363599,"domain_scores_codex":[0.9987286,0.00004907672,0.0003323314,0.0003732841,0.0002189893,0.0002977542],"domain_scores_gemma":[0.9992932,0.0001442855,0.00009540022,0.0002955339,0.0000879018,0.00008364468],"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":[0.000659773,0.0003155515,0.000001591294,0.0000340343,0.00005556117,9.171424e-7,0.0002720202,0.9702891,0.00001962913,0.003409453,0.0008566635,0.02408572],"study_design_scores_gemma":[0.003308157,0.0008946754,0.000002013582,0.0002703824,0.00008144278,3.086859e-7,0.0000809739,0.9086408,0.01206556,0.0000487658,0.0743572,0.0002496997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003673497,0.00004101446,0.9751658,0.000645451,0.0005499432,0.0005207448,0.000002614382,0.0001660219,0.02254109],"genre_scores_gemma":[0.9674221,0.00004548217,0.005181783,0.0006062074,0.0001342074,0.0003714172,0.00002649618,0.00004371663,0.02616864],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.969984,"threshold_uncertainty_score":0.9238864,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02480123187160449,"score_gpt":0.2774793029241693,"score_spread":0.2526780710525648,"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."}}