{"id":"W2000850397","doi":"10.1109/tac.2013.2292137","title":"Online Markov Decision Processes Under Bandit Feedback","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":102,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Hindsight bias; Markov decision process; Markov chain; State (computer science); Computer science; Markov process; Function (biology); Mathematical economics; Discrete mathematics; Combinatorics; Mathematical optimization; Mathematics; Artificial intelligence; Algorithm; Machine learning; Statistics; Psychology","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","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001955609,0.0003416131,0.0006459312,0.0007254864,0.0004606249,0.000362731,0.001024378,0.0001666199,0.003551582],"category_scores_gemma":[0.001704011,0.000246867,0.0002333298,0.001585769,0.0002050399,0.0005424485,0.000004497582,0.0003690331,0.002009625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001445872,"about_ca_system_score_gemma":0.0002410928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001469122,"about_ca_topic_score_gemma":0.0002879927,"domain_scores_codex":[0.9944181,0.0003872005,0.001049556,0.0007937693,0.002746422,0.0006049403],"domain_scores_gemma":[0.9868866,0.01071249,0.0002498053,0.001115936,0.000718261,0.0003169322],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001525382,0.0006083559,0.00001379932,0.00002407791,0.00005636388,0.000005917247,0.00009847568,0.06946191,0.000200153,0.00001207472,0.001134561,0.9282318],"study_design_scores_gemma":[0.005014583,0.0004719015,0.002837587,0.0001356546,0.00006299834,0.00003723185,0.0003188898,0.9653881,0.001554249,0.01853693,0.005186111,0.0004558167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02148839,0.00005010255,0.9747925,0.001530899,0.0007774307,0.0006319428,0.0001131907,0.0002832024,0.0003323022],"genre_scores_gemma":[0.9846848,0.00002141201,0.01143914,0.0006468864,0.0001372448,0.0001011012,0.000002857466,0.00004529736,0.002921241],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9633534,"threshold_uncertainty_score":0.9999983,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04329478899436651,"score_gpt":0.3667983632348631,"score_spread":0.3235035742404966,"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."}}