{"id":"W2888696679","doi":"10.1287/moor.2021.1168","title":"Multiplayer Bandits Without Observing Collision Information","year":2021,"lang":"en","type":"preprint","venue":"Mathematics of Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Institut de Valorisation des Données; Université de Montréal; Banco Bilbao Vizcaya Argentaria; Ministerio de Economía y Competitividad; Canada First Research Excellence Fund; Centre de Recherches Mathématiques; Fundación BBVA","keywords":"Regret; Logarithm; Collision; Square root; Computer science; Nash equilibrium; Square (algebra); Mathematical optimization; Root (linguistics); Mathematical economics; Mathematics; Computer security; Mathematical analysis; Machine learning; Geometry","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01472623,0.0003491875,0.0009620045,0.00210181,0.0007713684,0.003033222,0.002925479,0.0005060273,0.001118124],"category_scores_gemma":[0.04280111,0.0002783709,0.0002624699,0.002389373,0.0004221565,0.001882105,0.005239883,0.002037273,0.0005742277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003204503,"about_ca_system_score_gemma":0.001728819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000232365,"about_ca_topic_score_gemma":0.0004100826,"domain_scores_codex":[0.9857937,0.001021805,0.002393873,0.0007629242,0.009307857,0.0007198015],"domain_scores_gemma":[0.9797072,0.003774773,0.0003258872,0.002847374,0.01307755,0.0002672583],"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":[0.00005270423,0.0008468533,0.0005138811,0.0009842527,0.0001530179,0.00002419666,0.02009699,0.9541693,0.003143039,0.001950874,0.005389745,0.01267519],"study_design_scores_gemma":[0.0005667354,0.00008879149,0.0006798301,0.0006905843,0.00001346035,0.0000127374,0.01091922,0.9608988,0.01312146,0.01117322,0.001468973,0.0003662319],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5031856,0.0003857644,0.4878985,0.0009733553,0.0006271983,0.00287858,0.0003300622,0.00007096797,0.00365001],"genre_scores_gemma":[0.7704714,0.0002333813,0.2247549,0.00002036273,0.0001653992,0.0004227397,0.000312438,0.00005166616,0.003567749],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2672858,"threshold_uncertainty_score":0.9999669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4572293218497314,"score_gpt":0.5586788726154809,"score_spread":0.1014495507657495,"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."}}