{"id":"W4401508302","doi":"10.1109/meditcom61057.2024.10621193","title":"Online VNF Placement using Deep Reinforcement Learning and Reward Constrained Policy Optimization","year":2024,"lang":"en","type":"article","venue":"","topic":"Neuroscience and Neural Engineering","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Carleton University","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Distributed computing; Materials science","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":[0.0009606073,0.001273067,0.001298607,0.000430395,0.0003565288,0.0008840999,0.001387874,0.001296397,0.002293692],"category_scores_gemma":[0.003815266,0.0005624351,0.0004080151,0.0004207166,0.0008918709,0.001041129,0.001270259,0.001689441,0.0003205595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001214965,"about_ca_system_score_gemma":0.002076721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007173074,"about_ca_topic_score_gemma":0.007446875,"domain_scores_codex":[0.9995236,0.0001240248,0.00002157403,0.0001115364,0.0001026305,0.0001166734],"domain_scores_gemma":[0.9985017,0.0008978453,0.0001935599,0.00009567339,0.0001899299,0.0001213089],"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":[0.00002765816,0.00003604625,0.0002978323,0.00002546393,0.0000119785,0.00003547621,0.00001533141,0.978219,0.0006187467,0.002723244,0.000572042,0.0174172],"study_design_scores_gemma":[0.000002859022,0.000007870921,0.00001765771,0.00000224395,0.000001262456,0.000004099041,0.000001984495,0.9988192,0.00009802954,0.0009677974,0.00007573004,0.000001258506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02242206,0.0003511004,0.9732996,0.0003058322,0.00006890939,0.0000520608,0.00004141286,0.0005423583,0.00291677],"genre_scores_gemma":[0.8883786,0.0002333988,0.1077237,0.0002315391,0.00005762306,0.0001458096,0.0001032571,0.0001130292,0.00301316],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007173074,"threshold_uncertainty_score":0.01426262,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03625241261276976,"score_gpt":0.309229453708824,"score_spread":0.2729770410960543,"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."}}