{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001171711,0.00115378,0.001066469,0.0004393129,0.0002724298,0.001015628,0.001558191,0.001084223,0.001597212],"category_scores_gemma":[0.00225587,0.0004516597,0.0005450524,0.0003970693,0.001158526,0.0009536144,0.001222951,0.002079975,0.0003854087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000689283,"about_ca_system_score_gemma":0.001100902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003972547,"about_ca_topic_score_gemma":0.003099499,"domain_scores_codex":[0.9994856,0.0001644635,0.00002838776,0.0001240489,0.0001534156,0.00004400591],"domain_scores_gemma":[0.9992208,0.0004314083,0.000104311,0.00007690117,0.0001294526,0.00003701647],"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":[0.00004102407,0.00003983374,0.0003397026,0.0000654492,0.00003705134,0.00004964603,0.00004597357,0.9445742,0.001524483,0.01206899,0.0007120384,0.04050159],"study_design_scores_gemma":[0.000005365722,0.00001750564,0.00002646736,0.000003888386,0.000002696506,0.00000709434,0.000001684173,0.9969837,0.0002038958,0.002365827,0.0003792125,0.000002617275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002222591,0.0001220489,0.9956661,0.00009038276,0.00002791414,0.00002724965,0.00001117487,0.0001885083,0.001643886],"genre_scores_gemma":[0.701265,0.000486791,0.2927095,0.0002944698,0.000127346,0.0003088305,0.0001107888,0.0001623416,0.004534979],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003972547,"threshold_uncertainty_score":0.007898867,"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."}}