{"id":"W4280644846","doi":"10.1109/jsac.2022.3192053","title":"Hybrid Reinforcement Learning for STAR-RISs: A Coupled Phase-Shift Model Based Beamformer","year":2022,"lang":"en","type":"article","venue":"IEEE Journal on Selected Areas in Communications","topic":"Advanced Wireless Communication Technologies","field":"Engineering","cited_by":76,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"European Research Council; Engineering and Physical Sciences Research Council; China Scholarship Council","keywords":"Reinforcement learning; Computer science; Hybrid algorithm (constraint satisfaction); Markov decision process; Mathematical optimization; Algorithm; Transmission (telecommunications); Hybrid system; Markov process; Artificial intelligence; Constraint satisfaction; Mathematics; Telecommunications; Local consistency","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"],"consensus_categories":[],"category_scores_codex":[0.0005166622,0.0002382859,0.000301112,0.0006108961,0.001193838,0.00006259859,0.001957311,0.00005949517,0.00005953482],"category_scores_gemma":[0.0002698405,0.0002735382,0.0001064958,0.0007276104,0.00008304557,0.0002285548,0.0001935011,0.00218392,0.000004404087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009068558,"about_ca_system_score_gemma":0.0001915629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005834106,"about_ca_topic_score_gemma":0.00002168238,"domain_scores_codex":[0.9982064,0.0001642745,0.0007159407,0.0001597218,0.0003372589,0.0004164027],"domain_scores_gemma":[0.9972605,0.0007001684,0.0002670312,0.0014789,0.0002090481,0.00008431579],"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":[0.00008203227,0.0002461174,0.00003306139,0.00001050671,0.00004767549,9.874175e-7,0.0002207379,0.9913118,0.003330106,0.0008078798,0.0005625215,0.003346497],"study_design_scores_gemma":[0.002031738,0.0002826456,0.00002581236,0.00005112648,0.00001607219,0.0000158187,0.0002354622,0.9773281,0.002090968,0.001818029,0.01582022,0.000283992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08144112,0.0008292382,0.9138259,0.001600491,0.0001318633,0.0007434617,0.00004160032,0.0008500213,0.0005363458],"genre_scores_gemma":[0.9610736,0.001015588,0.03647828,0.000151633,0.00001628839,0.0009256636,0.0002057284,0.00007400366,0.00005916514],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8796325,"threshold_uncertainty_score":0.9999717,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03506494440618202,"score_gpt":0.3007106753041846,"score_spread":0.2656457308980026,"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."}}