{"id":"W2998970577","doi":"10.1109/jiot.2020.2965148","title":"Augmenting Drive-Thru Internet via Reinforcement Learning-Based Rate Adaptation","year":2020,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Wireless Networks and Protocols","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Computer science; Reinforcement learning; Computer network; The Internet; Scalability; Throughput; Wireless; Link adaptation; Adaptation (eye); Usability; Channel (broadcasting); Internet access; Automotive industry; Frame (networking); Distributed computing; Artificial intelligence; Telecommunications; Human–computer interaction; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008656465,0.0001999036,0.0002791891,0.0001065047,0.00007978536,0.0004081835,0.001144428,0.00007721655,0.0001551755],"category_scores_gemma":[0.00007611419,0.0001803151,0.0001840469,0.0001991709,0.00004205724,0.0009173513,0.000179674,0.0007268747,0.00004359299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000702634,"about_ca_system_score_gemma":0.00008156713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006391846,"about_ca_topic_score_gemma":0.00000219665,"domain_scores_codex":[0.9980171,0.0002018143,0.0007199774,0.000287082,0.000449628,0.0003244502],"domain_scores_gemma":[0.998397,0.0001040099,0.0009125901,0.0001654318,0.0002117553,0.0002091985],"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":[0.0002831351,0.00007457753,0.0007410264,0.0001225773,0.0002154911,0.0001129988,0.01779028,0.8961077,0.01228549,0.001192648,0.010186,0.06088809],"study_design_scores_gemma":[0.0007470112,0.0007394482,0.00005654621,0.0003427653,0.0000129249,0.00002940494,0.00003801653,0.9615185,0.03181077,0.0002934197,0.004230342,0.0001808491],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0120175,0.00003721882,0.9848441,0.00132862,0.0005993116,0.0005757036,1.039124e-7,0.00008337265,0.0005140397],"genre_scores_gemma":[0.9858997,0.00000610386,0.01165878,0.001662762,0.0002772867,0.00004665876,0.000001643197,0.00001751445,0.0004295907],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9738821,"threshold_uncertainty_score":0.7353038,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02713888185586617,"score_gpt":0.2508015832311625,"score_spread":0.2236627013752964,"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."}}