{"id":"W3101613519","doi":"","title":"Bias no more: high-probability data-dependent regret bounds for adversarial bandits and MDPs","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Regret; Markov decision process; Estimator; Upper and lower bounds; Computer science; Adversarial system; Mathematical optimization; Simple (philosophy); Schedule; Mathematics; Markov process; Artificial intelligence; Machine learning; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01646957,0.004575525,0.003468076,0.003085829,0.001692841,0.004410944,0.00573692,0.003838106,0.006686857],"category_scores_gemma":[0.07511774,0.001602742,0.002837521,0.002358396,0.005818111,0.009301647,0.008610031,0.01330776,0.00173062],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00532549,"about_ca_system_score_gemma":0.003550219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001737831,"about_ca_topic_score_gemma":0.001607496,"domain_scores_codex":[0.9916841,0.003502303,0.0002855506,0.001261103,0.002498962,0.0007680388],"domain_scores_gemma":[0.9359679,0.05181064,0.003054282,0.00504555,0.00270966,0.00141194],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003265787,0.000225704,0.001546878,0.000491923,0.0002093755,0.0002285424,0.0002572786,0.4678373,0.002725889,0.4798341,0.005646044,0.04067029],"study_design_scores_gemma":[0.00003077037,0.00006503845,0.0001928106,0.0001012005,0.00003988656,0.00006298484,0.0000181281,0.7768333,0.001443854,0.2195236,0.00165906,0.00002930176],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004024789,0.001058288,0.988189,0.001058732,0.0001123864,0.00007354683,0.0001210159,0.0003104027,0.005051901],"genre_scores_gemma":[0.60412,0.004422114,0.3689522,0.003273446,0.00123021,0.00146739,0.0006382229,0.001216827,0.01467969],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01646957,"threshold_uncertainty_score":0.08710045,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4996918330774113,"score_gpt":0.3266224601558188,"score_spread":0.1730693729215926,"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."}}