{"id":"W2157016390","doi":"","title":"Online Markov Decision Processes under Bandit Feedback","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":97,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Markov decision process; Computer science; Markov process; State (computer science); Markov chain; Mathematical optimization; Online learning; Reinforcement learning; Adversary; Function (biology); Action (physics); Artificial intelligence; Mathematics; Algorithm; Machine learning","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":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001768201,0.0002069261,0.0003031984,0.0004295078,0.000248245,0.0004532158,0.001547545,0.0001624998,0.01549713],"category_scores_gemma":[0.01300375,0.0001269714,0.00008957407,0.001960883,0.0002632757,0.0008039876,0.0004242027,0.0005772382,0.003017848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003055524,"about_ca_system_score_gemma":0.0003181225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000224762,"about_ca_topic_score_gemma":0.001808446,"domain_scores_codex":[0.9949963,0.00006221714,0.0006355422,0.0007894279,0.002988847,0.0005276378],"domain_scores_gemma":[0.9925805,0.004554091,0.0001335509,0.001066484,0.001347481,0.0003178499],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002176756,0.00074387,0.00434759,0.00001412027,0.00002268125,0.00004556599,0.0001329549,0.0008989897,0.003458509,0.0007470953,0.0825868,0.9067842],"study_design_scores_gemma":[0.002535532,0.0003036254,0.09904185,0.00004023132,0.00001228321,0.0001389178,0.001960583,0.01248573,0.01350072,0.4538599,0.4151506,0.0009700626],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4466851,0.0001413653,0.5336622,0.003357016,0.00157712,0.0004846028,0.00006962427,0.0002171841,0.01380572],"genre_scores_gemma":[0.8373506,0.00006453094,0.1110869,0.0006000394,0.000679378,0.00001912709,0.00001967251,0.0000444325,0.0501353],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9058141,"threshold_uncertainty_score":0.9977584,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08846169459235069,"score_gpt":0.4450109408182472,"score_spread":0.3565492462258965,"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."}}