{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008153588,0.0001286454,0.00009344539,0.0002162354,0.0001507619,0.0001676927,0.00007527844,0.00002821993,0.00008202552],"category_scores_gemma":[0.0002550497,0.0001113238,0.00002682998,0.0004840633,0.00007785776,0.0002985507,0.00008565388,0.0001505103,0.00000577008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005651909,"about_ca_system_score_gemma":0.00005330323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001010263,"about_ca_topic_score_gemma":7.247344e-7,"domain_scores_codex":[0.998965,0.00002595331,0.0001843723,0.0003513635,0.0002086078,0.0002646701],"domain_scores_gemma":[0.999709,0.00009093256,0.0000246795,0.00007475194,0.00000964364,0.00009107072],"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":[0.00000330216,0.000006296144,0.000004052557,0.00002065137,8.287754e-7,0.0000197539,0.00006394576,0.6229239,0.3746177,0.001625451,0.000003500333,0.0007107022],"study_design_scores_gemma":[0.0001227806,0.0000788999,0.00000188055,0.00003582299,0.000005125333,0.00007732892,0.00005610164,0.8950257,0.1038955,0.000008002628,0.0005779924,0.0001149105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3695203,0.0001163167,0.6219157,0.001430722,0.0007137954,0.0004932277,0.000003534913,0.0008868105,0.004919567],"genre_scores_gemma":[0.9959697,0.0002376418,0.001675361,0.0005991521,0.00008942656,0.00000337775,0.000002113523,0.00001808817,0.001405194],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6264493,"threshold_uncertainty_score":0.4539653,"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."}}