{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004521507,0.001183858,0.001975138,0.001039559,0.0004909746,0.001072428,0.001619025,0.001673662,0.002398897],"category_scores_gemma":[0.01306168,0.0003894109,0.0005495981,0.0009600121,0.001261824,0.002017632,0.001202797,0.002161746,0.0002658787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001772266,"about_ca_system_score_gemma":0.001794921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006302405,"about_ca_topic_score_gemma":0.002871855,"domain_scores_codex":[0.9979976,0.001064866,0.00007933588,0.0002322158,0.0004372034,0.0001887901],"domain_scores_gemma":[0.9895132,0.008767803,0.000443023,0.0004351566,0.0006387719,0.0002019862],"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":[0.0001160674,0.0001320432,0.0003168815,0.00006411871,0.00003502074,0.00001645981,0.00001436787,0.9652569,0.0001670791,0.005551312,0.0004722912,0.02785752],"study_design_scores_gemma":[0.000008045871,0.0000179173,0.00003310042,0.000003574627,0.000003005685,0.000003082623,0.000002259224,0.9984134,0.00005898194,0.001370372,0.0000847373,0.00000150039],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06138748,0.005195023,0.9223147,0.001170883,0.0002564167,0.0001553542,0.0000633289,0.0007665063,0.008690403],"genre_scores_gemma":[0.8695524,0.001415232,0.1257525,0.0003084769,0.0001870823,0.0001860088,0.00009563607,0.0001285806,0.002373964],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006302405,"threshold_uncertainty_score":0.02391231,"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."}}