{"id":"W4200629132","doi":"10.2139/ssrn.3978421","title":"Optimal No-Regret Learning in Strongly Monotone Games with Bandit Feedback","year":2021,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Monotone polygon; Mathematical economics; Mathematical optimization; Computer science; Mathematics; Economics; Machine learning","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":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00570812,0.0002685168,0.0004868844,0.0004727908,0.000337246,0.0004935674,0.0008690569,0.0001150522,0.0007737867],"category_scores_gemma":[0.002370358,0.0001927417,0.0001460773,0.001518314,0.0001696642,0.0008535529,0.0001890948,0.004981122,0.0005115265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001141019,"about_ca_system_score_gemma":0.005417934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003236711,"about_ca_topic_score_gemma":0.001284747,"domain_scores_codex":[0.9923294,0.0005432355,0.0006995134,0.0006749954,0.002354707,0.00339815],"domain_scores_gemma":[0.9974706,0.0006532565,0.0003074374,0.0004360214,0.0009074549,0.0002252352],"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":[0.002001683,0.0005799948,0.07693838,0.0000119651,0.0004599747,0.001607257,0.001216537,0.6488621,0.001664546,0.006164292,0.001138983,0.2593542],"study_design_scores_gemma":[0.03635082,0.01472534,0.08872917,0.0007064646,0.0001654424,0.02522609,0.1246829,0.212716,0.009410544,0.3255944,0.1566336,0.005059168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7958539,0.004440777,0.1956219,0.001604387,0.0002452022,0.0002244541,0.000004754587,0.00005131125,0.001953341],"genre_scores_gemma":[0.9610536,0.001644713,0.002867937,0.0000261558,0.0004109069,0.00001157511,0.000006116737,0.00004739608,0.03393166],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4361461,"threshold_uncertainty_score":0.9973145,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0280459300877103,"score_gpt":0.3506929644061739,"score_spread":0.3226470343184636,"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."}}