{"id":"W4381734451","doi":"10.1109/noms56928.2023.10154411","title":"A Deep Reinforcement Learning Framework for Optimizing Congestion Control in Data Centers","year":2023,"lang":"en","type":"article","venue":"","topic":"Peer-to-Peer Network Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); University of Toronto","funders":"","keywords":"Reinforcement learning; Network congestion; Computer science; Delegate; Leverage (statistics); Distributed computing; Data center; Latency (audio); Network traffic control; Throughput; Computer network; Artificial intelligence; Network packet","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":[0.0007021651,0.0001210574,0.0001672759,0.0002776032,0.00009247035,0.0001548621,0.001776333,0.00009753736,0.000004231829],"category_scores_gemma":[0.000808796,0.0001181526,0.00002605283,0.0008678739,0.00002175112,0.0004179344,0.001128,0.0002264833,0.00005766819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007361259,"about_ca_system_score_gemma":0.00002264733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000024457,"about_ca_topic_score_gemma":0.00004280182,"domain_scores_codex":[0.9985589,0.00003030606,0.0002409328,0.0004873753,0.0002062845,0.0004762032],"domain_scores_gemma":[0.9984811,0.0004541472,0.0000638448,0.0009030539,0.00004170738,0.00005618007],"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":[0.00001835742,0.000008638415,0.0007656598,0.000009458879,0.00001615212,0.00001030484,0.000248707,0.8961538,0.00008256637,0.05988124,0.003800659,0.03900442],"study_design_scores_gemma":[0.000446965,0.00007611821,0.0003745435,0.00006333744,0.000003067297,0.000001304556,0.0001589904,0.9912897,0.00006238654,0.003291228,0.004089191,0.0001431208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007636439,0.00002484042,0.9866567,0.01021699,0.0002892906,0.0004963899,8.997849e-7,0.001342911,0.0002083],"genre_scores_gemma":[0.5758945,0.00001965713,0.4229804,0.0007233808,0.00003019366,0.0001012459,0.00002678535,0.000009793729,0.0002140146],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5751309,"threshold_uncertainty_score":0.4818121,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04674521707238224,"score_gpt":0.3024139925197962,"score_spread":0.255668775447414,"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."}}