{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001199451,0.0003484053,0.0009206455,0.001045921,0.00007719279,0.00009428375,0.002421695,0.0003557593,0.0005487799],"category_scores_gemma":[0.003193288,0.0003557647,0.0003204959,0.002327309,0.0003660329,0.0003977472,0.003604572,0.001731667,0.0002095334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000235215,"about_ca_system_score_gemma":0.0003369869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002107893,"about_ca_topic_score_gemma":0.0001346661,"domain_scores_codex":[0.9958888,0.0005729373,0.0007332119,0.001613134,0.0006866083,0.0005052511],"domain_scores_gemma":[0.9961521,0.001388922,0.0006395408,0.001094404,0.000460438,0.0002645954],"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":[0.000390633,0.0002239287,0.03746153,0.00007212615,0.00007795692,0.0008654913,0.000616703,0.9524162,0.0007677011,0.001928975,0.0004017605,0.004776976],"study_design_scores_gemma":[0.001201799,0.0001641974,0.02010708,0.0001476979,0.00002785424,0.000002525991,0.001538811,0.8588946,0.0005608881,0.1147633,0.002109943,0.0004813614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8748254,0.0001433791,0.1230913,0.000203806,0.0002590029,0.0003883926,0.00009630588,0.00007763375,0.0009148703],"genre_scores_gemma":[0.9937565,0.0002916042,0.0006862312,0.00002103048,0.0001148242,8.928611e-7,0.00004682823,0.00003269076,0.005049442],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.122405,"threshold_uncertainty_score":0.9998894,"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."}}