{"id":"W3111828395","doi":"10.1109/twc.2020.3022705","title":"Centralized and Distributed Deep Reinforcement Learning Methods for Downlink Sum-Rate Optimization","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Wireless Communications","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Telecommunications link; Mathematical optimization; Maximization; Convergence (economics); Optimization problem; Transmitter power output; Artificial intelligence; Algorithm; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003962808,0.0001953444,0.0002494083,0.0000861023,0.0008064196,0.0001792063,0.001100736,0.00008792395,0.000006761138],"category_scores_gemma":[0.00005786114,0.0002087872,0.0001125481,0.0004961216,0.0001312053,0.0003807997,0.00002685796,0.0003751583,0.000004648353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008943716,"about_ca_system_score_gemma":0.00005825222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000021086,"about_ca_topic_score_gemma":0.00001372022,"domain_scores_codex":[0.9983627,0.0004929765,0.0003808937,0.0003590375,0.0001116339,0.0002927928],"domain_scores_gemma":[0.9976309,0.0008742348,0.0001730462,0.0009335223,0.000203513,0.000184769],"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":[0.00003949696,0.00007824972,0.000004659868,0.00001650153,0.00008126676,2.268658e-7,0.0008348122,0.8430474,0.0008772339,0.00843057,0.000006993629,0.1465826],"study_design_scores_gemma":[0.001017025,0.0001543323,0.00001192897,0.00001730823,0.00005309659,0.000001704834,0.0000888592,0.9950805,0.0007918607,0.0001318703,0.002443239,0.0002082518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00005413306,0.000123343,0.989764,0.008756427,0.00009347905,0.0007561928,0.00001900429,0.0003999856,0.00003347487],"genre_scores_gemma":[0.5523112,0.0002956831,0.4467357,0.0002907122,0.000007183801,0.0002651855,0.00005570806,0.0000144735,0.00002418829],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.552257,"threshold_uncertainty_score":0.8514095,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03467231661912773,"score_gpt":0.3130906819506749,"score_spread":0.2784183653315472,"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."}}