{"id":"W3084085014","doi":"","title":"Bandit Online Learning of Nash Equilibria in Monotone Games","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Nash equilibrium; Monotonic function; Monotone polygon; Regular polygon; Mathematical optimization; Action (physics); Extension (predicate logic); Mathematical economics; Function (biology); Mathematics; Zero (linguistics); Best response; Computer science; Zero-sum game","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":[0.003278703,0.001290022,0.001805048,0.0006673151,0.0008171623,0.001832123,0.002401042,0.001781281,0.002478083],"category_scores_gemma":[0.0166514,0.0006214508,0.0006357775,0.0008119897,0.002007738,0.003186012,0.002119322,0.002383752,0.0005937763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001325245,"about_ca_system_score_gemma":0.001290094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002761685,"about_ca_topic_score_gemma":0.002525869,"domain_scores_codex":[0.9982047,0.0008967064,0.00008250489,0.0003190291,0.0002842725,0.0002128335],"domain_scores_gemma":[0.9908065,0.007062616,0.0007479809,0.0005413234,0.0006064037,0.0002351214],"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":[0.0003124398,0.000333466,0.001393251,0.0002080095,0.0001118196,0.0001201863,0.0001986414,0.8125141,0.001853368,0.1053757,0.00130667,0.07627244],"study_design_scores_gemma":[0.0000154626,0.00003218708,0.00004444299,0.000009770001,0.000006241541,0.00001120431,0.000009736536,0.9720195,0.000463495,0.02718524,0.0001979592,0.000004873431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03410301,0.0001979089,0.961557,0.000327399,0.00003408551,0.00008097196,0.00003544644,0.0002243196,0.00343987],"genre_scores_gemma":[0.8549549,0.000252901,0.1403053,0.0002273749,0.00006741586,0.0003020439,0.00009792369,0.00008318509,0.00370897],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003278703,"threshold_uncertainty_score":0.01733965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2829365411725819,"score_gpt":0.3283189320134625,"score_spread":0.04538239084088058,"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."}}