{"id":"W4315630035","doi":"10.1109/globecom48099.2022.10001554","title":"Hierarchical Reinforcement Learning for RIS-Assisted Energy-Efficient RAN","year":2022,"lang":"en","type":"article","venue":"GLOBECOM 2022 - 2022 IEEE Global Communications Conference","topic":"Advanced Wireless Communication Technologies","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ericsson (Canada); University of Ottawa","funders":"","keywords":"Reinforcement learning; Base station; Computer science; Efficient energy use; Energy consumption; Throughput; Controller (irrigation); Transmission (telecommunications); Computer network; Radio access network; Power control; Distributed computing; Wireless; Power (physics); Artificial intelligence; Telecommunications; Engineering; Electrical engineering","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0004683829,0.0003783178,0.0004250752,0.0002009014,0.001949626,0.0001021369,0.004358558,0.0001214983,0.0004287474],"category_scores_gemma":[0.0001708049,0.0004733972,0.0002014369,0.001258966,0.0003346958,0.0001336152,0.002517435,0.00118252,0.00002192612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001203025,"about_ca_system_score_gemma":0.0001597329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001052372,"about_ca_topic_score_gemma":0.0001525955,"domain_scores_codex":[0.9972662,0.0004123329,0.0007549302,0.0004265504,0.0005169878,0.0006229655],"domain_scores_gemma":[0.9955437,0.0004563364,0.0002297447,0.003443384,0.0001899526,0.0001368872],"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":[0.00004413198,0.0001713638,0.0001064254,0.00002805411,0.0001046875,0.000001608933,0.0001942681,0.8038026,0.001303119,0.1289083,0.004549928,0.06078548],"study_design_scores_gemma":[0.0007542875,0.0001361089,0.0002053942,0.00002064155,0.00002972725,0.00002180678,0.001637927,0.781244,0.0003722202,0.004061026,0.2110041,0.0005127124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01271608,0.006370015,0.94526,0.003305166,0.001036805,0.001398771,0.0005915824,0.003963557,0.02535801],"genre_scores_gemma":[0.9834547,0.001848927,0.01062395,0.0001512884,0.00001913013,0.00262154,0.0008223722,0.00004890588,0.0004091587],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9707386,"threshold_uncertainty_score":0.9997718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03462045193845421,"score_gpt":0.2795320782949604,"score_spread":0.2449116263565062,"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."}}