{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007590103,0.0001006782,0.0001271685,0.00006147009,0.0000310489,0.0000457811,0.00008304527,0.00005113862,0.00001514394],"category_scores_gemma":[0.000003417138,0.00009734828,0.00001682363,0.0002447671,0.000003348438,0.0004546087,0.000005968871,0.0001026968,0.00001117358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001181668,"about_ca_system_score_gemma":0.000007259634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008492472,"about_ca_topic_score_gemma":0.0001493823,"domain_scores_codex":[0.9994091,0.00001000343,0.000164508,0.0001308708,0.00006203118,0.0002234528],"domain_scores_gemma":[0.9998101,0.00002894427,0.00003863623,0.00006875616,0.00003111496,0.00002243062],"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":[0.00003725727,0.000002855759,0.003121905,0.00007114968,0.0000109326,2.944084e-7,0.000113566,0.9951985,0.0001009442,0.00001290861,0.00008002901,0.00124968],"study_design_scores_gemma":[0.0005611692,0.0000647131,0.0003220139,0.00006978169,0.000004644241,0.0000020879,0.00001805128,0.9977007,0.0006403112,0.000006839544,0.000475675,0.0001340128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1313888,0.00004140661,0.8670783,0.000004519151,0.0003076857,0.0005501837,6.426305e-8,0.0001691799,0.0004598471],"genre_scores_gemma":[0.9968512,0.0000097623,0.002543519,0.00001677149,0.00015569,0.0001194862,0.000009080036,0.00003988733,0.0002545868],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8654624,"threshold_uncertainty_score":0.3969748,"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."}}