{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006025058,0.001639483,0.002389413,0.000774823,0.001064078,0.002874845,0.002633716,0.003043856,0.001676407],"category_scores_gemma":[0.02000481,0.0008338852,0.001360325,0.001233412,0.003425526,0.003011739,0.003084616,0.00276079,0.0004653943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002116095,"about_ca_system_score_gemma":0.001686862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002027609,"about_ca_topic_score_gemma":0.001240767,"domain_scores_codex":[0.9946764,0.00266699,0.0001800008,0.0007854932,0.0007421059,0.0009490511],"domain_scores_gemma":[0.9852809,0.01070429,0.001595228,0.001092647,0.0006343409,0.0006924905],"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":[0.0003580715,0.0001219727,0.0008491413,0.0001081458,0.0001111924,0.0002653758,0.0001323304,0.8836059,0.001488198,0.1061936,0.001163666,0.005602449],"study_design_scores_gemma":[0.00003664833,0.00007049189,0.0001337103,0.00001376077,0.00001592006,0.00005695644,0.00002825378,0.9452104,0.0003540688,0.05383158,0.0002349223,0.0000133044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1386164,0.0006513917,0.8448364,0.001832472,0.00009896597,0.0001054384,0.0002043953,0.0002512264,0.01340345],"genre_scores_gemma":[0.9608389,0.0002407937,0.03472192,0.0003796098,0.0001256341,0.0001741235,0.0000836412,0.00004891028,0.003386355],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006025058,"threshold_uncertainty_score":0.03186393,"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."}}