{"id":"W3197830211","doi":"10.1109/lcn52139.2021.9524965","title":"Transfer Learning-Based Accelerated Deep Reinforcement Learning for 5G RAN Slicing","year":2021,"lang":"en","type":"article","venue":"","topic":"Software-Defined Networks and 5G","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ericsson (Canada); Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Slicing; Transfer of learning; Resource allocation; Convergence (economics); Base station; Radio access network; Ran; Cellular network; Resource management (computing); Distributed computing; Reduction (mathematics); Artificial intelligence; Computer network; World Wide Web","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":[0.0003127652,0.0001878323,0.0002304127,0.00007481768,0.0003776065,0.0002934984,0.0003555144,0.0000924342,0.0002592336],"category_scores_gemma":[0.0001349064,0.0001733948,0.0001491647,0.0005507849,0.00001638302,0.0003183259,0.00004021241,0.0002836909,0.00002809313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004229822,"about_ca_system_score_gemma":0.0001255188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003352523,"about_ca_topic_score_gemma":0.00002835941,"domain_scores_codex":[0.9984179,0.00008796774,0.000304914,0.0004676437,0.0002473163,0.0004742213],"domain_scores_gemma":[0.9989116,0.0004130587,0.00003891057,0.0002993757,0.0002199771,0.0001170956],"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":[0.00001990787,0.00002246447,0.0005244086,0.0000237063,0.00002369811,0.00001148667,0.0002928195,0.9736218,0.001008814,0.004043244,0.0002521542,0.02015549],"study_design_scores_gemma":[0.001379168,0.0001896748,0.0001605647,0.00003475444,0.00001139791,0.000003885968,0.00006600234,0.9564212,0.02407657,0.00007154069,0.01732661,0.0002586467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009067583,0.0001117091,0.9868121,0.0008982272,0.0002311298,0.0002060227,7.105217e-8,0.0005511804,0.002121956],"genre_scores_gemma":[0.9844941,0.00001823176,0.01067136,0.00184706,0.00009385053,0.00005173113,0.00003272152,0.00002386506,0.002767006],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9761407,"threshold_uncertainty_score":0.7070836,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02743457370962348,"score_gpt":0.2507560846093334,"score_spread":0.2233215108997099,"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."}}