{"id":"W2963875807","doi":"10.1109/tcomm.2017.2734768","title":"Dynamic Spectrum Access in Time-Varying Environment: Distributed Learning Beyond Expectation Optimization","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Communications","topic":"Cognitive Radio Networks and Spectrum Sensing","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Performance metric; Mathematical optimization; Metric (unit); Q-learning; Nash equilibrium; Quality of service; Ordinal optimization; Potential game; Convergence (economics); Reinforcement learning; Mathematics; Artificial intelligence; Ordinal regression; Machine learning; Computer network","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0002231886,0.0001721665,0.000176966,0.0002387435,0.002043306,0.0008131397,0.002207813,0.00007986845,0.00005135269],"category_scores_gemma":[0.00001650312,0.0002039858,0.00008231535,0.0002723743,0.0001375874,0.00135632,0.0000511841,0.0005245873,0.00004894405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002508003,"about_ca_system_score_gemma":0.00003766052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008676232,"about_ca_topic_score_gemma":0.0001877495,"domain_scores_codex":[0.9986412,0.0002051315,0.0003025447,0.0003563589,0.0002209017,0.0002738617],"domain_scores_gemma":[0.9974532,0.0002536579,0.0002237929,0.001965521,0.00003139967,0.00007245099],"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":[0.00001007083,0.0002040524,0.0001393662,0.000002532354,0.0000215433,0.000003598624,0.0003601275,0.9816108,0.0001849349,0.0001785645,0.000005169875,0.01727928],"study_design_scores_gemma":[0.0004578056,0.00003805484,0.003257026,0.00006533622,0.00001506212,0.000008592872,0.00002538956,0.9946488,0.0005939259,0.000597659,0.00007974778,0.0002125923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00325368,0.00007200192,0.9912384,0.003452584,0.0001313577,0.000250294,0.00001179958,0.0001481539,0.00144178],"genre_scores_gemma":[0.9821745,0.0009909031,0.01652614,0.00004164926,0.0000107611,0.00004248741,0.00004476727,0.00001921181,0.0001495695],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9789208,"threshold_uncertainty_score":0.9992559,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0204099317678246,"score_gpt":0.2739983472998319,"score_spread":0.2535884155320073,"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."}}