{"id":"W4313136702","doi":"10.1109/tsmc.2022.3214221","title":"Reinforcement Learning-Based Feedback and Weight-Adjustment Mechanisms for Consensus Reaching in Group Decision Making","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Systems","topic":"Multi-Criteria Decision Making","field":"Decision Sciences","cited_by":47,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick; University of Windsor","funders":"Agencia Estatal de Investigación; Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Markov decision process; Computer science; Scalability; Harmony (color); Artificial intelligence; Group decision-making; Reinforcement; Decision problem; Notation; Machine learning; Markov process; Mathematics; Statistics; Psychology; Algorithm; Social psychology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00528838,0.0004409112,0.0008300972,0.001177843,0.001014575,0.0007639474,0.0004953828,0.0001660624,0.00007057714],"category_scores_gemma":[0.0001411315,0.0003944921,0.0001703709,0.0006229837,0.00008091925,0.0001216386,0.00003120448,0.0005474241,0.00001995217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004333126,"about_ca_system_score_gemma":0.00006305581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003202769,"about_ca_topic_score_gemma":0.0001227364,"domain_scores_codex":[0.9929954,0.001146103,0.001952985,0.001163255,0.002174929,0.0005673335],"domain_scores_gemma":[0.9944341,0.003729827,0.0006958218,0.0007298655,0.000197199,0.0002131672],"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":[0.0006691894,0.0001642956,0.000109138,0.0001307393,0.0000463275,0.00004075015,0.001211464,0.9653867,0.001185881,0.003081939,0.0004246655,0.02754893],"study_design_scores_gemma":[0.003380543,0.000875366,0.0002346689,0.0006356805,0.00005112083,0.0002230285,0.007954601,0.9719977,0.00008319624,0.0009811503,0.01303998,0.0005429973],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09154713,0.0008766741,0.9003169,0.00008560574,0.004427087,0.002287302,0.00006883342,0.00009004756,0.0003004068],"genre_scores_gemma":[0.9954934,0.00002646718,0.002044054,0.00008896417,0.00007654685,0.0007049427,0.000005058812,0.00006456595,0.001496026],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9039462,"threshold_uncertainty_score":0.9998507,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06285006846990177,"score_gpt":0.3260461768517512,"score_spread":0.2631961083818494,"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."}}