{"id":"W4402158975","doi":"10.1109/icc51166.2024.10623091","title":"Online Optimization for Network Resource Allocation and Comparison with Reinforcement Learning Techniques","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Reinforcement learning; Computer science; Resource allocation; Resource management (computing); Resource (disambiguation); Artificial intelligence; Distributed computing; Computer network","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":[0.001435272,0.00009434725,0.000152076,0.0001755205,0.000190683,0.0003693638,0.0001631465,0.00004742719,0.0001122453],"category_scores_gemma":[0.0004636588,0.00006012675,0.00002261157,0.0006466854,0.00006679102,0.000313905,0.00008113887,0.0001542132,0.000005930411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000458254,"about_ca_system_score_gemma":0.00004186659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007176829,"about_ca_topic_score_gemma":0.0000204993,"domain_scores_codex":[0.9983292,0.00006198732,0.0003417037,0.00036363,0.000692517,0.0002109514],"domain_scores_gemma":[0.9984914,0.0009526976,0.00006871518,0.0001767268,0.0002493154,0.00006114934],"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":[0.00004566037,0.000009508681,0.0001365659,0.000008714026,0.0000075317,6.989887e-7,0.0001046513,0.875971,0.00001298808,0.0006608339,0.003675836,0.119366],"study_design_scores_gemma":[0.0001014901,0.000299442,0.00003971742,0.00004388716,0.000004789165,0.0000028227,0.0004324358,0.8502237,0.0004837574,0.00075805,0.1475322,0.00007765336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000403318,0.0002920337,0.9965726,0.001096002,0.00003026886,0.0004742985,0.000001306058,0.0001953629,0.0009347875],"genre_scores_gemma":[0.2783701,0.00008987547,0.7030767,0.0001224613,0.0003579513,0.0001135065,0.0001264606,0.00003403639,0.01770893],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2934959,"threshold_uncertainty_score":0.3561784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08962090951805965,"score_gpt":0.4361140075983547,"score_spread":0.346493098080295,"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."}}