{"id":"W2927073559","doi":"10.1109/access.2019.2904539","title":"Deep Reinforcement Learning for Router Selection in Network With Heavy Traffic","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced MIMO Systems Optimization","field":"Engineering","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Key Laboratory of Universal Wireless Communications of Ministry of Education; Natural Science Foundation of Beijing Municipality; Beijing University of Posts and Telecommunications; National Natural Science Foundation of China","keywords":"Computer science; Computer network; Reinforcement learning; Routing protocol; Network congestion; Distributed computing; Static routing; Wireless network; Router; Markov decision process; Routing (electronic design automation); Markov process; Wireless; Artificial intelligence; Network packet; Telecommunications","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":[0.001270962,0.0006946133,0.0009592957,0.0003819122,0.000355826,0.0006263031,0.001195008,0.0009225643,0.00124077],"category_scores_gemma":[0.003206163,0.0003952169,0.0002959215,0.0003403229,0.0009202566,0.0009601831,0.0008773308,0.001280003,0.0001398146],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001298193,"about_ca_system_score_gemma":0.001390255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007042106,"about_ca_topic_score_gemma":0.006498165,"domain_scores_codex":[0.9995895,0.0001250465,0.00001508495,0.0000973026,0.00005955549,0.0001134717],"domain_scores_gemma":[0.9983784,0.00104208,0.0001805276,0.00005511965,0.0002239974,0.0001199165],"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":[0.00006333684,0.00004138169,0.0008420593,0.00002427008,0.00001682734,0.00004230247,0.00001903401,0.9791989,0.0006485278,0.003397195,0.0006496881,0.01505646],"study_design_scores_gemma":[0.000002672612,0.000006265149,0.00002315685,8.102043e-7,0.000001244257,0.000001867096,0.000001451704,0.9991875,0.00005861804,0.0006912844,0.00002420941,8.013052e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09206387,0.0005343519,0.9037366,0.0006726915,0.00008149564,0.00004221202,0.00005255074,0.0004088192,0.002407459],"genre_scores_gemma":[0.9712464,0.0001290182,0.0268543,0.0001806637,0.00002906027,0.00004553589,0.00005890569,0.00002466887,0.001431408],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007042106,"threshold_uncertainty_score":0.01400226,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00920604080058962,"score_gpt":0.2383131341612013,"score_spread":0.2291070933606117,"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."}}