{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001696399,0.0007610564,0.001181606,0.001359124,0.0008684388,0.001067352,0.002365306,0.000338716,0.01096671],"category_scores_gemma":[0.001712842,0.0004805943,0.0002504102,0.006197701,0.001515516,0.001720198,0.0009652926,0.001416733,0.001069268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002731977,"about_ca_system_score_gemma":0.002938194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001481357,"about_ca_topic_score_gemma":0.0007682467,"domain_scores_codex":[0.9913055,0.0004208555,0.001500565,0.002135138,0.003222634,0.001415249],"domain_scores_gemma":[0.9917552,0.003539523,0.0002666326,0.001821073,0.002092779,0.0005247672],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004687914,0.007200415,0.009312949,0.0002106558,0.001967812,0.002085424,0.004346575,0.03677998,0.0007086182,0.007641503,0.1558156,0.7692425],"study_design_scores_gemma":[0.01383162,0.005588881,0.02630683,0.001547599,0.0002866207,0.0001549985,0.03220618,0.5903814,0.03979241,0.03420455,0.2523257,0.003373233],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03863303,0.002604321,0.8644701,0.007439375,0.001075914,0.001810201,0.0003219412,0.0001225851,0.0835225],"genre_scores_gemma":[0.574279,0.001260391,0.05313465,0.003260734,0.0005071089,0.0001193071,0.0000625047,0.00008196422,0.3672944],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8113355,"threshold_uncertainty_score":0.9999697,"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."}}