{"id":"W4381744996","doi":"10.1109/noms56928.2023.10154267","title":"Generalizable Resource Scaling of 5G Slices using Constrained Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Software-Defined Networks and 5G","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Rogers Communications (Canada); University of Waterloo","funders":"","keywords":"Computer science; Quality of service; Traffic classification; Reinforcement learning; Slicing; Leverage (statistics); Computer network; Distributed computing; Robustness (evolution); Artificial intelligence","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":[0.0004674373,0.0001059919,0.0001667516,0.0001400065,0.0001720207,0.00008781614,0.0003835288,0.00005013874,0.00004760812],"category_scores_gemma":[0.00004998769,0.00009477261,0.00006222302,0.000869018,0.00004182099,0.0001834066,0.0002051092,0.00009385894,0.0000219717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001870628,"about_ca_system_score_gemma":0.00004319085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002029761,"about_ca_topic_score_gemma":0.000002629711,"domain_scores_codex":[0.9988266,0.00004564567,0.0002886341,0.0002490043,0.000262874,0.0003271993],"domain_scores_gemma":[0.9993371,0.0001469971,0.0001189563,0.000277205,0.0000529449,0.00006679563],"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":[0.00000288241,0.000005292908,0.001248784,0.0000171765,0.00001596919,0.000006334498,0.0004275247,0.9749918,0.00155614,0.01615936,0.0008145698,0.00475414],"study_design_scores_gemma":[0.0002133897,0.0000366865,0.0001360219,0.00004792558,0.000004836899,0.000005461764,0.0001333517,0.9906912,0.002234635,0.0002580806,0.006110562,0.0001278694],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.083129,0.00009701666,0.9046907,0.0001493177,0.0001577956,0.0001008221,2.626743e-7,0.0006204403,0.01105466],"genre_scores_gemma":[0.9305139,0.00002440504,0.06618213,0.0002741715,0.00009674048,0.000004065331,0.000006868758,0.00001396464,0.002883776],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8473849,"threshold_uncertainty_score":0.3864715,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03690780235266578,"score_gpt":0.2638742983015502,"score_spread":0.2269664959488845,"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."}}