{"id":"W7123346749","doi":"10.1109/cdc57313.2025.11312073","title":"Online bandit non-cooperative games with arbitrary delays","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Regret; Online learning; Order (exchange); Upper and lower bounds; Multi-armed bandit; Online algorithm","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":[0.001630714,0.001460653,0.001297925,0.0003449048,0.000613028,0.001540076,0.001787025,0.001327701,0.001768852],"category_scores_gemma":[0.006775407,0.0003870027,0.0005333585,0.0006770752,0.001361891,0.001954636,0.001294474,0.001638231,0.0002518563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001648037,"about_ca_system_score_gemma":0.00114662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005113817,"about_ca_topic_score_gemma":0.003556208,"domain_scores_codex":[0.9988067,0.0003841072,0.00004917974,0.0002518641,0.0001996662,0.0003084105],"domain_scores_gemma":[0.9959061,0.00288278,0.0005347863,0.0002323824,0.0002384725,0.0002053296],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001951299,0.00007062947,0.0004623778,0.00005309903,0.00002301025,0.000158717,0.00004749582,0.9516244,0.0009840054,0.03666614,0.0004391177,0.00927594],"study_design_scores_gemma":[0.0000127634,0.00002756167,0.00004891359,0.000003724496,0.000006090464,0.00001688095,0.00001325571,0.9900373,0.0003258272,0.009271589,0.0002309069,0.000005138614],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08522318,0.0004444578,0.907454,0.0003745416,0.00009183861,0.00008835968,0.0001096073,0.0002030694,0.006011005],"genre_scores_gemma":[0.9760561,0.0002288266,0.02004108,0.0001052749,0.00003501187,0.00009826414,0.0000481388,0.0000202501,0.003366964],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005113817,"threshold_uncertainty_score":0.01195741,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04362770102241034,"score_gpt":0.4100376357551577,"score_spread":0.3664099347327474,"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."}}