{"id":"W3123348991","doi":"10.1145/3543846","title":"Reinforcement Learning based Recommender Systems: A Survey","year":2022,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":470,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Recommender system; Reinforcement learning; Computer science; Markov decision process; RSS; Artificial intelligence; Collaborative filtering; Scalability; Field (mathematics); Machine learning; Markov process; World Wide Web; Database","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":[0.001802136,0.001582715,0.002813711,0.001395345,0.0005213214,0.001848063,0.002280756,0.002171319,0.004045798],"category_scores_gemma":[0.004411734,0.0008074213,0.001394933,0.003298565,0.0004992628,0.002365377,0.001169558,0.001769622,0.002575771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008354644,"about_ca_system_score_gemma":0.0009587978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005825875,"about_ca_topic_score_gemma":0.003935474,"domain_scores_codex":[0.9986519,0.0003872256,0.0001673509,0.0003208043,0.0004020696,0.00007061013],"domain_scores_gemma":[0.9970999,0.002013458,0.0001140038,0.0001938997,0.0005049686,0.00007384539],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001680923,0.0004077675,0.003870065,0.004680406,0.000422828,0.0002196996,0.0002065555,0.05802228,0.001402503,0.02302722,0.02279702,0.8847756],"study_design_scores_gemma":[0.0001860613,0.001114561,0.006564917,0.002407195,0.0008322729,0.001767378,0.0003757048,0.4569521,0.002686787,0.06082753,0.4659819,0.0003036063],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00796116,0.7489542,0.224203,0.002392685,0.0009100275,0.0002043794,0.0004094529,0.0005855907,0.01437949],"genre_scores_gemma":[0.1428986,0.7181669,0.1230908,0.001376569,0.00335406,0.0003552189,0.001250913,0.0001442452,0.009362745],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.005825875,"threshold_uncertainty_score":0.01353449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1741681475714232,"score_gpt":0.3564372636552874,"score_spread":0.1822691160838642,"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."}}