{"id":"W3083274012","doi":"","title":"Centralized & Distributed Deep Reinforcement Learning Methods for Downlink Sum-Rate Optimization","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Telecommunications link; Mathematical optimization; Maximization; Convergence (economics); Optimization problem; Rate of convergence; State (computer science); Artificial intelligence; Algorithm; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001049568,0.0006968394,0.0008077406,0.0001858928,0.0002470491,0.0006175352,0.0007908575,0.000724928,0.001265749],"category_scores_gemma":[0.002354108,0.0003020971,0.0003163105,0.0002448964,0.0007937847,0.0006308702,0.0007581587,0.001225176,0.0002032238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007886747,"about_ca_system_score_gemma":0.001100588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004074241,"about_ca_topic_score_gemma":0.003795005,"domain_scores_codex":[0.9996504,0.0001309777,0.00001059017,0.00007769284,0.00008148269,0.00004887785],"domain_scores_gemma":[0.9991766,0.0004965894,0.00009925245,0.00006558473,0.0001186137,0.0000434216],"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":[0.00002903924,0.00002431325,0.0001423202,0.00001863882,0.00001197343,0.00001725062,0.00001341961,0.9836863,0.0006215214,0.003364458,0.0003311378,0.01173956],"study_design_scores_gemma":[0.000002742925,0.000006750108,0.00001206329,8.301053e-7,8.888403e-7,0.000001629114,0.000001023907,0.9991178,0.00009521171,0.0007091886,0.00005107906,6.698597e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01712161,0.0002011369,0.9800838,0.0001831696,0.00002762829,0.00002124175,0.00001615998,0.0002507792,0.002094493],"genre_scores_gemma":[0.929237,0.000134062,0.06782749,0.00008841103,0.00003050361,0.00007349326,0.00003529731,0.00005047174,0.002523418],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004074241,"threshold_uncertainty_score":0.008101046,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06386126489103415,"score_gpt":0.2417486656383556,"score_spread":0.1778874007473215,"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."}}