{"id":"W3133904720","doi":"10.23919/icact51234.2021.9370861","title":"TCP Congestion Avoidance in Data Centres using Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Network Traffic and Congestion Control","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; TCP tuning; Computer network; Zeta-TCP; TCP Friendly Rate Control; Reinforcement learning; TCP acceleration; Network congestion; Throughput; TCP Westwood plus; H-TCP; The Internet; Transmission Control Protocol; Artificial intelligence; Network packet; Telecommunications; Wireless; World Wide Web","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":[0.0002656892,0.00008490996,0.0001122946,0.00004129037,0.00008061342,0.0001380477,0.0005253397,0.00003614432,0.00007477648],"category_scores_gemma":[0.00008751312,0.0000850788,0.0000169316,0.0003082773,0.00001581915,0.0005355021,0.000409566,0.0001571989,0.0000301405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000404578,"about_ca_system_score_gemma":0.0001272119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003940593,"about_ca_topic_score_gemma":0.0001474352,"domain_scores_codex":[0.9988908,0.0001064356,0.0002056839,0.0003848109,0.0001845145,0.0002277209],"domain_scores_gemma":[0.9991605,0.00009006693,0.0000556908,0.0005789317,0.0000655166,0.00004926511],"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":[0.000008127357,0.00004267033,0.005048423,0.000009558374,0.00001606629,0.0001079128,0.0001594767,0.5968333,0.0005741348,0.06668489,0.0007127253,0.3298027],"study_design_scores_gemma":[0.0003890005,0.000007672082,0.000756979,0.00003892688,0.000003116888,0.00001292933,0.00004964599,0.9865899,0.0001291117,0.00007559216,0.01183951,0.0001075762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01471651,0.0005038388,0.9796793,0.00144258,0.0003396274,0.00007903465,3.416824e-7,0.0001402415,0.003098507],"genre_scores_gemma":[0.982749,0.00006056684,0.01473735,0.0004857966,0.00007045041,0.000002365189,0.00001380853,0.000004253408,0.001876345],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9680325,"threshold_uncertainty_score":0.3469413,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04299066574049768,"score_gpt":0.2721910091896834,"score_spread":0.2292003434491857,"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."}}