{"id":"W2135829225","doi":"10.1109/gamenets.2009.5137416","title":"Online learning in Markov decision processes with arbitrarily changing rewards and transitions","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Markov decision process; Regret; Computer science; Markov chain; Transition (genetics); Decision maker; Markov process; Range (aeronautics); Trajectory; Control (management); Online learning; Mathematical optimization; Artificial intelligence; Machine learning; Mathematics; Operations research; Statistics; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.001231568,0.0001379446,0.0002429138,0.0009241845,0.0002135271,0.000204029,0.0002736771,0.00005863066,0.0001495617],"category_scores_gemma":[0.002478128,0.00008834984,0.00002373729,0.002890507,0.00008782669,0.0006696425,0.0000419618,0.0003379284,0.00001402213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003345326,"about_ca_system_score_gemma":0.0001566934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009752012,"about_ca_topic_score_gemma":0.0006395647,"domain_scores_codex":[0.9974195,0.00007680108,0.0003570584,0.00050843,0.001226607,0.0004116319],"domain_scores_gemma":[0.9980451,0.001218115,0.00006060295,0.0002217706,0.0003282385,0.0001261349],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003456699,0.000283091,0.003382374,0.00001367533,0.000005737496,0.0001394706,0.002288145,0.008832759,0.0002736459,0.0001406286,0.0001391608,0.9841557],"study_design_scores_gemma":[0.01078174,0.005118829,0.5122403,0.001560623,0.00003650938,0.0007101194,0.04888381,0.2200656,0.004341031,0.1756793,0.01825636,0.002325839],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5296431,0.0003424833,0.4646851,0.002681282,0.00002410777,0.0002618881,0.00000769984,0.00009047304,0.002263834],"genre_scores_gemma":[0.9477227,0.0001252111,0.04992584,0.0002199005,0.00004762978,0.000006486533,0.000005846547,0.00001010323,0.001936234],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9818298,"threshold_uncertainty_score":0.3602802,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04799188361605175,"score_gpt":0.3932287474444243,"score_spread":0.3452368638283726,"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."}}