{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001790659,0.00024504,0.0004297595,0.0001724928,0.000382919,0.0002329682,0.002075097,0.0001505049,0.0004325291],"category_scores_gemma":[0.005999921,0.0002190081,0.0001041269,0.0009469407,0.0004910465,0.001376605,0.001475392,0.0002988329,0.0003756173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001288049,"about_ca_system_score_gemma":0.0002108631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001083505,"about_ca_topic_score_gemma":0.0001008436,"domain_scores_codex":[0.9964843,0.0002431102,0.0003831628,0.001791346,0.0005937628,0.000504312],"domain_scores_gemma":[0.9954483,0.001765795,0.0002195232,0.001479409,0.000595301,0.0004916547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.03024148,0.002124143,0.1523327,0.0006676053,0.001601962,0.003835455,0.007445528,0.3265043,0.00209289,0.1103113,0.2962667,0.06657602],"study_design_scores_gemma":[0.008123971,0.000938822,0.009787599,0.00002012688,0.0001364528,0.00001080709,0.0011947,0.7701097,0.0005519349,0.1308418,0.07729671,0.0009874461],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.524582,0.00006850003,0.4694996,0.001994529,0.0008187478,0.001162063,0.001167442,0.0001667285,0.000540451],"genre_scores_gemma":[0.9947318,0.00004327637,0.002119778,0.0002090461,0.0003653231,0.000001488333,0.0000750926,0.00002111089,0.002433041],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4701499,"threshold_uncertainty_score":0.8930889,"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."}}