{"id":"W2154806059","doi":"","title":"Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions","year":2013,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Markov decision process; Adversarial system; Mathematical optimization; Computer science; Shortest path problem; Path (computing); Mathematics; Graph; Markov process; Theoretical computer science; Artificial intelligence; 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":[],"consensus_categories":[],"category_scores_codex":[0.0008362065,0.0001880977,0.0002774641,0.0003812722,0.0002710759,0.0001384353,0.0006841978,0.0001103397,0.0005255857],"category_scores_gemma":[0.003206552,0.0001516327,0.00006826699,0.003513002,0.0002767522,0.001617349,0.0001386163,0.0004213669,0.0002107991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002789394,"about_ca_system_score_gemma":0.0003478482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002483123,"about_ca_topic_score_gemma":0.002024487,"domain_scores_codex":[0.9975822,0.0002716363,0.0003464018,0.0008870009,0.000477142,0.0004356508],"domain_scores_gemma":[0.996471,0.001662052,0.0001501212,0.0004968787,0.001024103,0.0001958385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0009215675,0.00116255,0.08742838,0.0000498238,0.00003467846,0.0002400455,0.0006842311,0.8692603,0.0001539202,0.0009159154,0.0002712579,0.03887735],"study_design_scores_gemma":[0.004910219,0.0007634845,0.4226949,0.0002264318,0.00003866932,0.00002188369,0.004359107,0.3705978,0.0003259136,0.1933522,0.001858214,0.0008512603],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6124066,0.000009288739,0.3867233,0.000182465,0.00002783926,0.0003930951,0.00002405117,0.00005392599,0.0001793752],"genre_scores_gemma":[0.9958372,0.00004200714,0.003085784,0.00001663518,0.00003346277,0.000003702331,0.00004005854,0.00001197623,0.0009291801],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4986625,"threshold_uncertainty_score":0.61834,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09547229580583252,"score_gpt":0.270794819568804,"score_spread":0.1753225237629715,"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."}}