{"id":"W4313477458","doi":"10.1109/mcom.004.2200532","title":"Reinforcement Learning for Radio Resource Management in RAN Slicing: A Survey","year":2023,"lang":"en","type":"article","venue":"IEEE Communications Magazine","topic":"Software-Defined Networks and 5G","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Reinforcement learning; Radio access network; Markov decision process; Radio resource management; Resource allocation; Wireless network; Resource management (computing); Computer network; Distributed computing; Cellular network; Markov process; Wireless; Artificial intelligence; Base station; Telecommunications","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":[0.0017495,0.001319159,0.001896372,0.0009068992,0.0004314382,0.002060973,0.001893387,0.001769831,0.002577428],"category_scores_gemma":[0.003891048,0.000625646,0.001101535,0.002177543,0.0009802898,0.002387319,0.001133647,0.002208296,0.0008889231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001069244,"about_ca_system_score_gemma":0.001203554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002868612,"about_ca_topic_score_gemma":0.001808128,"domain_scores_codex":[0.9989747,0.0003223847,0.0001025428,0.0002481971,0.0002752059,0.00007703973],"domain_scores_gemma":[0.9975536,0.001924834,0.0001057336,0.0001063049,0.0002447588,0.00006480108],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001192143,0.0003361632,0.001959091,0.003019821,0.0001894279,0.0001679261,0.0002406494,0.2413573,0.001324468,0.06378233,0.009575506,0.6779281],"study_design_scores_gemma":[0.00005489173,0.0003673248,0.001476295,0.001167704,0.0001339873,0.0003355443,0.0002254322,0.8386195,0.001621154,0.07486594,0.08103447,0.00009768279],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.007376553,0.3008175,0.670498,0.002344056,0.000587124,0.000132823,0.0001112989,0.0004067138,0.01772602],"genre_scores_gemma":[0.2978754,0.4568036,0.2274236,0.001595601,0.003428367,0.0004608636,0.0004909101,0.000291875,0.01162975],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.002868612,"threshold_uncertainty_score":0.009252369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06601169914195948,"score_gpt":0.3041308803824594,"score_spread":0.2381191812405,"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."}}