{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.02767136,0.0009732876,0.002813956,0.0007125895,0.0008280029,0.0009384042,0.005972231,0.0003760963,0.0001079003],"category_scores_gemma":[0.001273823,0.000896759,0.0007025976,0.001743602,0.00003266443,0.0002502147,0.004224309,0.001733013,0.00007788145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006988487,"about_ca_system_score_gemma":0.0006744001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002706409,"about_ca_topic_score_gemma":0.00003882462,"domain_scores_codex":[0.973051,0.02144155,0.002041107,0.001539303,0.0009296226,0.0009974163],"domain_scores_gemma":[0.9868389,0.007656803,0.001809009,0.003312782,0.0001638381,0.0002187134],"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":[5.618753e-7,0.00005002484,0.0001286862,0.00457874,0.0001951689,0.00002473336,0.00007046889,0.001402675,5.535226e-9,0.0003423528,0.009104919,0.9841017],"study_design_scores_gemma":[0.000163112,0.0001560989,0.00004607646,0.003413262,0.00004773148,0.000047515,0.000009594238,0.03329724,1.181969e-7,0.00001928228,0.9618634,0.000936553],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.496941e-7,0.5127753,0.4825767,0.00002624696,0.002013845,0.0008447751,0.000009525224,0.0009091152,0.0008443609],"genre_scores_gemma":[0.0004854767,0.9896454,0.007358492,0.0001121847,0.0002516682,0.0002818433,0.0009851402,0.0001765653,0.0007032763],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9831651,"threshold_uncertainty_score":0.9994059,"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."}}