{"id":"W3153573172","doi":"10.1109/tnnls.2021.3070584","title":"Multiagent Meta-Reinforcement Learning for Adaptive Multipath Routing Optimization","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Software-Defined Networks and 5G","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Toronto Metropolitan University","funders":"National Natural Science Foundation of China","keywords":"Reinforcement learning; Computer science; Markov decision process; Routing (electronic design automation); Node (physics); Multipath routing; Adaptive routing; Multi-agent system; Distributed computing; Network packet; Artificial intelligence; Markov process; Dynamic Source Routing; Computer network; Routing protocol; Engineering","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":[0.001117512,0.001031968,0.001174178,0.000461956,0.0003951265,0.0006999419,0.001089217,0.001018668,0.001251905],"category_scores_gemma":[0.002357487,0.0004410954,0.0005873531,0.0004280315,0.0008590041,0.0007313727,0.001012561,0.001251837,0.0001747757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009818086,"about_ca_system_score_gemma":0.001080068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00514067,"about_ca_topic_score_gemma":0.003604891,"domain_scores_codex":[0.9996276,0.000152847,0.00001699275,0.0000701089,0.00007302377,0.00005931471],"domain_scores_gemma":[0.9990181,0.0006084931,0.0001369332,0.00005885045,0.0001181553,0.0000594899],"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":[0.00001205421,0.00001057411,0.0001321522,0.00001222793,0.00001904598,0.00001664779,0.000009405068,0.9930395,0.0001586706,0.002461697,0.0001270983,0.00400081],"study_design_scores_gemma":[0.000002381698,0.000005564311,0.00001116587,8.609223e-7,0.000001525396,0.000001460268,0.000001051231,0.999022,0.00002885374,0.0008771582,0.00004722462,7.675692e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02133508,0.0005439427,0.9753376,0.0002790305,0.00005685795,0.00002777199,0.00002611232,0.0002602038,0.002133325],"genre_scores_gemma":[0.9448964,0.000233958,0.05278312,0.0001088254,0.00004335748,0.0001128403,0.00004347291,0.00004014059,0.001737915],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00514067,"threshold_uncertainty_score":0.01022148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.038082896844584,"score_gpt":0.2436636899350177,"score_spread":0.2055807930904338,"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."}}