{"id":"W3017748691","doi":"10.1109/tccn.2020.2988908","title":"Delay-Aware VNF Scheduling: A Reinforcement Learning Approach With Variable Action Set","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Cognitive Communications and Networking","topic":"Software-Defined Networks and 5G","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Reinforcement learning; Markov decision process; Distributed computing; Scheduling (production processes); Quality of service; Q-learning; Integer programming; Mathematical optimization; Markov process; Computer network; Algorithm; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001506513,0.00105479,0.001420425,0.0005675496,0.0004302133,0.0007678592,0.00192561,0.001122072,0.001614509],"category_scores_gemma":[0.002966959,0.0004577294,0.0005509852,0.0005278775,0.0009098839,0.0007800407,0.0008997619,0.001491406,0.0001581197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001415992,"about_ca_system_score_gemma":0.00191269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009540848,"about_ca_topic_score_gemma":0.006669924,"domain_scores_codex":[0.9992815,0.0002530233,0.00002846813,0.0001546779,0.0001472068,0.0001351182],"domain_scores_gemma":[0.9986032,0.0008831777,0.0001919675,0.00004581234,0.000177219,0.00009858212],"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":[0.00002547441,0.00003204866,0.0001957522,0.00002272827,0.00001741228,0.00003280855,0.00001920875,0.9869171,0.0002885601,0.003109224,0.0001934901,0.009146155],"study_design_scores_gemma":[0.000005211687,0.00001258215,0.00001963264,0.000002021178,0.000002606687,0.000003793413,0.000002077196,0.9988239,0.00006037743,0.0009727775,0.00009313569,0.000001853083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01638012,0.0003148005,0.9803167,0.0002460352,0.00005772604,0.0000636413,0.00002923168,0.0001946258,0.002397222],"genre_scores_gemma":[0.8862398,0.0002839626,0.1107987,0.0001685602,0.00006603433,0.0002308111,0.00006795094,0.00004807651,0.002096022],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009540848,"threshold_uncertainty_score":0.01897067,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08454553673967595,"score_gpt":0.278670215954831,"score_spread":0.1941246792151551,"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."}}