{"id":"W3199320363","doi":"10.1109/tcomm.2021.3113948","title":"Scalable Deep Reinforcement Learning for Routing and Spectrum Access in Physical Layer","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Communications","topic":"Advanced MIMO Systems Optimization","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Reinforcement learning; Computer network; Scalability; Dynamic Source Routing; Bottleneck; Distributed computing; Wireless network; Physical layer; Static routing; Wireless Routing Protocol; Routing (electronic design automation); Routing protocol; Destination-Sequenced Distance Vector routing; Wireless ad hoc network; Network topology; Wireless; Artificial intelligence; Telecommunications","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":[0.00007607451,0.0001028217,0.0001370439,0.00009124239,0.0002483159,0.00005883223,0.0001837362,0.00004450466,0.00001218662],"category_scores_gemma":[0.0000115131,0.0001249734,0.00004045721,0.0003072103,0.00002660117,0.000287902,0.00000603044,0.0002687617,0.000005658481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001157931,"about_ca_system_score_gemma":0.00001774446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002148451,"about_ca_topic_score_gemma":0.0004465252,"domain_scores_codex":[0.9994004,0.00004242825,0.0002039309,0.0001295712,0.00005588539,0.0001677293],"domain_scores_gemma":[0.9991722,0.0002314033,0.00002882098,0.0004849473,0.00004408299,0.00003856605],"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":[0.000003205201,0.00004380258,0.00002541268,0.00002595162,0.00001733081,2.437315e-7,0.0003829618,0.9953469,0.001467898,0.000324661,0.000004773321,0.00235686],"study_design_scores_gemma":[0.0003707389,0.00001587653,0.00005696345,0.00005920344,0.00001689226,0.000003459292,0.00023768,0.9830782,0.01547231,0.0001981962,0.0003661973,0.0001243098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002924911,0.0001385757,0.9945973,0.0002533724,0.00009361302,0.0002586196,0.000002602349,0.0001531178,0.001577905],"genre_scores_gemma":[0.9932768,0.0004079262,0.005734703,0.00001727811,0.00001654573,0.0002249159,0.0000169878,0.00003054224,0.0002743029],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9903519,"threshold_uncertainty_score":0.5096268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03049595639539128,"score_gpt":0.2931182854124724,"score_spread":0.2626223290170811,"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."}}