{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001148503,0.0007898961,0.0009485689,0.0002153349,0.0002681291,0.0006457053,0.0009364367,0.0007814621,0.001341918],"category_scores_gemma":[0.002693545,0.000344737,0.0003627334,0.0002757754,0.0008155027,0.0007099176,0.0008308293,0.001443689,0.0002225874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000821923,"about_ca_system_score_gemma":0.001219337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003886093,"about_ca_topic_score_gemma":0.003915517,"domain_scores_codex":[0.9995953,0.0001533632,0.00001314653,0.00008420984,0.00009758084,0.00005637085],"domain_scores_gemma":[0.9989682,0.000636011,0.0001193949,0.00007316138,0.0001486666,0.00005452979],"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":[0.00003092008,0.00003043618,0.0001541999,0.00002140518,0.00001354499,0.00001926903,0.00001648074,0.9827612,0.0006066414,0.003342453,0.0003409506,0.01266243],"study_design_scores_gemma":[0.000002842763,0.000007476886,0.00001126514,8.766055e-7,9.799594e-7,0.000001915486,0.00000117396,0.9992466,0.0000914663,0.0005890808,0.00004561952,7.587756e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01391783,0.0002067508,0.9836584,0.0001481475,0.00002630728,0.00002107185,0.00001357854,0.0002379079,0.00177003],"genre_scores_gemma":[0.9185174,0.0001542387,0.07870009,0.00009291866,0.00003374463,0.00008610258,0.00003844236,0.00005535356,0.002321738],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003886093,"threshold_uncertainty_score":0.007726967,"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."}}