{"id":"W2948647439","doi":"10.48550/arxiv.1902.01239","title":"A Practical Algorithm for Multiplayer Bandits when Arm Means Vary Among Players","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Sublinear function; Computer science; Minimax; Matching (statistics); Mathematical optimization; Collision; Algorithm; Mathematics; Machine learning; Discrete mathematics; Computer security; Statistics","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","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002780988,0.0007113402,0.001098748,0.001122731,0.0004072589,0.0004629575,0.002827005,0.0009397115,0.0009300323],"category_scores_gemma":[0.003267182,0.0006778305,0.0007847963,0.0009327256,0.0005580414,0.00127407,0.002793206,0.001876189,0.001164275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006083723,"about_ca_system_score_gemma":0.0008832329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001747035,"about_ca_topic_score_gemma":0.0001378061,"domain_scores_codex":[0.9931946,0.000552372,0.0007898121,0.00307826,0.001208327,0.001176575],"domain_scores_gemma":[0.9883873,0.00630309,0.0008169304,0.002459123,0.001394724,0.0006388183],"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":[0.001102923,0.00116784,0.008720304,0.0001512781,0.0009839593,0.002075764,0.001243096,0.8917615,0.00002992037,0.004859461,0.06165558,0.02624832],"study_design_scores_gemma":[0.002008616,0.0002049219,0.001045366,0.00007710534,0.0001240545,0.00001277978,0.0008268534,0.9257993,0.0001621747,0.05765396,0.01127832,0.0008066177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01772735,0.0000407703,0.9756459,0.0002289239,0.001758743,0.002118386,0.0005803115,0.0001710536,0.001728583],"genre_scores_gemma":[0.8880637,0.0001278817,0.06924141,0.0001496994,0.0006643317,0.00002598835,0.000155161,0.0001449977,0.04142683],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9064045,"threshold_uncertainty_score":0.9999833,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2895327430734515,"score_gpt":0.3426463910670395,"score_spread":0.05311364799358798,"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."}}