{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002258763,0.0002345858,0.0002216425,0.00009692632,0.001277101,0.0002432152,0.0005515547,0.0000993215,0.00001171263],"category_scores_gemma":[0.000004481261,0.0002222997,0.00005975139,0.000946658,0.0001144461,0.0004205385,0.00003386696,0.0007952846,0.00001018723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004014881,"about_ca_system_score_gemma":0.00007333949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003055706,"about_ca_topic_score_gemma":0.00001403421,"domain_scores_codex":[0.9985451,0.000196554,0.0002708049,0.0004482519,0.0002165914,0.0003227554],"domain_scores_gemma":[0.9984446,0.0005053015,0.0001493826,0.0005327053,0.0001892779,0.0001786934],"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":[0.0002141573,0.000237356,0.0002753282,0.00006702773,0.0003291689,0.000005324052,0.003431052,0.497268,0.00004922907,0.001646746,0.00007011359,0.4964065],"study_design_scores_gemma":[0.0007721813,0.0004008644,0.00001755334,0.000231615,0.00008139492,0.00002904505,0.0005475972,0.9928209,0.0000870724,0.00007235067,0.004637062,0.0003023538],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008207305,0.0006441155,0.9956354,0.0005710945,0.0001077307,0.0003349358,0.000003916852,0.0003467054,0.001535328],"genre_scores_gemma":[0.9536921,0.00253102,0.04251349,0.0009140166,0.00008875972,0.0001535039,0.00003026119,0.00002617189,0.00005061949],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.953122,"threshold_uncertainty_score":0.9822561,"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."}}