{"id":"W3174263485","doi":"","title":"Cooperative and Stochastic Multi-Player Multi-Armed Bandit: Optimal Regret With Neither Communication Nor Collisions","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Randomness; Intuition; Computer science; Mathematical economics; Mathematical optimization; Fictitious play; Mathematics; Game theory; Machine learning; 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":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002272641,0.0002745413,0.0004223906,0.0002196037,0.000801171,0.0004665267,0.0006521441,0.0001324946,0.001445497],"category_scores_gemma":[0.009764556,0.0001901895,0.00005132662,0.0006781371,0.0008184698,0.0002846546,0.0003726801,0.0009979575,0.0003259573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006731567,"about_ca_system_score_gemma":0.0004030881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007704017,"about_ca_topic_score_gemma":0.00005466572,"domain_scores_codex":[0.9957889,0.001689111,0.0003940951,0.0007850388,0.0009274557,0.0004153894],"domain_scores_gemma":[0.992115,0.005055907,0.0002323253,0.0009085574,0.001454778,0.0002334359],"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":[0.003524124,0.00139379,0.005852679,0.00002606818,0.0003434855,0.0003423078,0.02663151,0.7613249,0.006077575,0.06926664,0.0006268469,0.1245901],"study_design_scores_gemma":[0.006472008,0.00108325,0.01878445,0.0004850189,0.00004972678,0.0001069215,0.0342658,0.9262654,0.002385345,0.006503107,0.002637378,0.0009616342],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1200905,0.0003077664,0.876941,0.000800645,0.00007278096,0.0004373982,0.00003685238,0.00008756394,0.001225471],"genre_scores_gemma":[0.9584697,0.00007075501,0.01947684,0.0001105353,0.00002644101,0.00006686257,0.00002513696,0.00003700025,0.0217167],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8574642,"threshold_uncertainty_score":0.9994673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1626154911242037,"score_gpt":0.4264370049582369,"score_spread":0.2638215138340332,"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."}}