{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007206075,0.0004482084,0.0005621315,0.0001704272,0.0002876111,0.0002543624,0.001845035,0.0003170878,0.00001731021],"category_scores_gemma":[0.000444716,0.0005330066,0.0003825855,0.000641124,0.00008877637,0.0003842718,0.001843851,0.0006927816,0.00001384232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005085742,"about_ca_system_score_gemma":0.0002253612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004702916,"about_ca_topic_score_gemma":0.000004314425,"domain_scores_codex":[0.9969401,0.0005914313,0.0003798644,0.001384164,0.00009185205,0.0006125594],"domain_scores_gemma":[0.99747,0.0004084391,0.0006034057,0.0008468164,0.0003914877,0.0002798051],"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":[0.0001022298,0.00002799786,0.00006993089,0.00006696248,0.0001907774,0.00003223171,0.0001634741,0.9251369,0.00005337553,0.0708722,0.00002420684,0.003259696],"study_design_scores_gemma":[0.001428805,0.0001198371,0.00003955464,0.0000438389,0.000163897,9.799412e-7,0.00004331737,0.9881786,0.00007260835,0.00761522,0.001769086,0.0005242376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002096089,0.0000555377,0.9968551,0.0003912796,0.0005083934,0.001212754,0.00001462344,0.0006409299,0.0001117763],"genre_scores_gemma":[0.6236598,0.00009245738,0.3751806,0.000121526,0.0000641792,0.00001176679,0.0005309411,0.00003019806,0.0003084602],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6234502,"threshold_uncertainty_score":0.9997122,"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."}}