{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00168858,0.0001377535,0.0001882095,0.0003408265,0.0003100821,0.0001118947,0.002194326,0.00004830334,0.000004055664],"category_scores_gemma":[0.0001389106,0.000146103,0.00006293159,0.001752407,0.00004770974,0.0001571435,0.0007643814,0.0002312517,0.0001609218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007927115,"about_ca_system_score_gemma":0.00002288791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006156272,"about_ca_topic_score_gemma":0.0002397674,"domain_scores_codex":[0.9985218,0.0002568937,0.0003805818,0.0002896514,0.0001838164,0.0003672518],"domain_scores_gemma":[0.9964446,0.001106749,0.0001113853,0.002201867,0.00007168237,0.0000636465],"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":[0.0001024476,0.0003021047,0.01352347,0.0001209706,0.0001776655,0.00001923803,0.00347177,0.5296435,0.0001391665,0.06211295,0.2251433,0.1652434],"study_design_scores_gemma":[0.001130379,0.0000738213,0.03900718,0.000066638,0.000008606436,0.000002409119,0.00005419939,0.6524901,0.0000123991,0.0006907955,0.3062323,0.0002311062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005617851,0.0006327493,0.968062,0.006372938,0.0004581379,0.001531717,0.000004391159,0.001252033,0.01606816],"genre_scores_gemma":[0.9496425,0.001243239,0.03846409,0.000472453,0.00006463503,0.0005905788,0.0002849618,0.00003984419,0.0091977],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9440246,"threshold_uncertainty_score":0.5957907,"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."}}