{"id":"W659523800","doi":"","title":"Evaluation and Analysis of the Performance of the EXP3 Algorithm in Stochastic Environments","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Computer science; Algorithm; Logarithm; Stochastic process; Adversarial system; Artificial intelligence; Mathematical optimization; Mathematics; 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":[0.002647249,0.0000608858,0.0001796711,0.0002470589,0.00005867449,0.00002048089,0.0005407099,0.00002928917,0.0008780953],"category_scores_gemma":[0.001032745,0.00002669012,0.00006599887,0.001735046,0.0002567851,0.0002437413,0.0002738545,0.00008642006,0.00001509483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004566226,"about_ca_system_score_gemma":0.00003903714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008975736,"about_ca_topic_score_gemma":0.00004746301,"domain_scores_codex":[0.9964492,0.0002770592,0.0003899196,0.0002023005,0.002555357,0.0001261573],"domain_scores_gemma":[0.9985639,0.0005111185,0.0001800472,0.0005512491,0.0001683426,0.00002533499],"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":[0.000005488374,0.00008487834,0.09414473,0.000001756388,0.0001080869,4.346863e-8,0.0007668289,0.2249738,0.002294933,0.00001166311,0.0000564677,0.6775513],"study_design_scores_gemma":[0.0001090703,0.00001150384,0.4605617,0.000002756125,0.00002777864,1.280447e-7,0.0001931024,0.5371946,0.00129535,0.0005806789,0.000004949381,0.00001840015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9665046,0.00005818763,0.03271622,0.0001215425,0.00004254161,0.0004299119,0.000005378242,0.000001024864,0.0001205844],"genre_scores_gemma":[0.9984183,0.000008307662,0.0007220399,0.00001294388,0.000004405953,0.00002769964,4.272683e-7,0.000002502,0.000803338],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6775329,"threshold_uncertainty_score":0.9614528,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07402534430139121,"score_gpt":0.3945074600203065,"score_spread":0.3204821157189153,"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."}}