{"id":"W4404520129","doi":"10.22541/au.173204444.43700477/v1","title":"MaxExp-UCB: Enhanced Regret Bounds for Normalized Exploration Stochastic Multi-Armed Bandit Problems With High Action Spaces","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Regret; Action (physics); Mathematical optimization; Mathematical economics; Computer science; Mathematics; Machine learning; Physics","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":[0.008632421,0.003432356,0.002925337,0.001336113,0.001326749,0.004101277,0.004129617,0.002793209,0.008246473],"category_scores_gemma":[0.03145847,0.00107723,0.001751559,0.002099732,0.0029257,0.00577677,0.004864847,0.007027647,0.002040727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003492576,"about_ca_system_score_gemma":0.004130732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003248748,"about_ca_topic_score_gemma":0.003750147,"domain_scores_codex":[0.9951079,0.001995312,0.0001875951,0.0006810432,0.001221582,0.0008066006],"domain_scores_gemma":[0.9824921,0.01260702,0.0009699789,0.00169701,0.001458536,0.0007753188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00055409,0.0002770554,0.001066782,0.0004882604,0.0001185466,0.000146483,0.000141525,0.8676566,0.001836358,0.0654363,0.01069482,0.05158323],"study_design_scores_gemma":[0.00002256288,0.00007815327,0.0001478502,0.00008308264,0.00001626061,0.00004721516,0.00001955092,0.9757391,0.0005136881,0.02200971,0.001308775,0.00001400889],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01579946,0.005313489,0.9600964,0.001777582,0.0003079128,0.0001906326,0.0004025322,0.001121117,0.01499089],"genre_scores_gemma":[0.5850204,0.004356425,0.3874685,0.002769905,0.0008987891,0.001474394,0.001379419,0.001499278,0.01513287],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008632421,"threshold_uncertainty_score":0.04565316,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0590815207010501,"score_gpt":0.3127189573357616,"score_spread":0.2536374366347115,"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."}}