{"id":"W4411921768","doi":"10.1137/23m1592559","title":"Unsynchronized Decentralized Q-Learning: Two Timescale Analysis by Persistence","year":2025,"lang":"en","type":"article","venue":"SIAM Journal on Control and Optimization","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University; University of Toronto","funders":"","keywords":"Persistence (discontinuity); Mathematics; Q-learning; Artificial intelligence; Computer science; Engineering; Geotechnical engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.001984971,0.0001644411,0.0004661494,0.0007814349,0.0005990636,0.000674389,0.0003794504,0.00007540995,0.0008157552],"category_scores_gemma":[0.00250844,0.0001174793,0.000220092,0.002066942,0.0001193307,0.0003996379,0.00004290521,0.0004180418,0.00002317717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001162937,"about_ca_system_score_gemma":0.0001151082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004018386,"about_ca_topic_score_gemma":0.000005111995,"domain_scores_codex":[0.9969326,0.0006116655,0.0005983423,0.0004112811,0.00109676,0.0003493016],"domain_scores_gemma":[0.9973791,0.001189389,0.0003052159,0.0002233425,0.0006862138,0.0002166948],"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":[0.0003052101,0.00005096601,0.00298489,0.00000124606,0.0002448142,0.000008384911,0.00004974774,0.9751493,0.00009550466,0.00006430805,0.001637886,0.01940775],"study_design_scores_gemma":[0.00469699,0.0001344144,0.00101898,0.00001595428,0.0001900902,0.000008490541,0.0001840722,0.9846611,0.00005919738,0.0008716692,0.008030058,0.0001289929],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001766226,0.001846379,0.9922019,0.002858141,0.0001580638,0.0001718639,0.000009416698,0.00002566835,0.0009623495],"genre_scores_gemma":[0.9760312,0.001288858,0.01159542,0.0006262615,0.00008164914,0.00001009337,0.00001687944,0.00001386825,0.01033574],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9806065,"threshold_uncertainty_score":0.8931947,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0234439653790888,"score_gpt":0.3643506722537654,"score_spread":0.3409067068746766,"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."}}