{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01026909,0.00155171,0.001244796,0.0008826749,0.0006800538,0.0013738,0.001889548,0.002222068,0.002757838],"category_scores_gemma":[0.03298193,0.0003439085,0.0006252611,0.001315371,0.001726,0.002098849,0.001907797,0.002156527,0.0005766826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001847797,"about_ca_system_score_gemma":0.002238027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003432089,"about_ca_topic_score_gemma":0.002739959,"domain_scores_codex":[0.9947895,0.002594729,0.0002630248,0.0005125222,0.001413637,0.0004265629],"domain_scores_gemma":[0.9642159,0.02827828,0.001608182,0.002736732,0.00240576,0.0007551306],"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":[0.001116034,0.0003004372,0.002889509,0.0002061182,0.00007697667,0.00008083899,0.00004407711,0.9534169,0.001580961,0.00909309,0.002317841,0.02887719],"study_design_scores_gemma":[0.00006035991,0.0002365098,0.0005890162,0.0000151521,0.000009098317,0.00005870946,0.00001715534,0.9940808,0.001074546,0.003541507,0.0003058386,0.00001129467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4795412,0.00477376,0.4927114,0.001888169,0.0003042861,0.0004832513,0.001149701,0.001775728,0.01737246],"genre_scores_gemma":[0.8696679,0.0006238166,0.126195,0.0002699381,0.00007436733,0.000168897,0.001068969,0.0002197161,0.001711538],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01026909,"threshold_uncertainty_score":0.05430877,"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."}}