{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005595752,0.0006550056,0.0006599124,0.0001795862,0.0001994992,0.0005026804,0.0009451327,0.0006804882,0.001615064],"category_scores_gemma":[0.001021907,0.0003268194,0.0004366315,0.0003003104,0.0006023205,0.000577106,0.0007331361,0.001104375,0.0004771111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004373455,"about_ca_system_score_gemma":0.0008058397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003425166,"about_ca_topic_score_gemma":0.003540018,"domain_scores_codex":[0.9997057,0.00008248786,0.0000133537,0.00007581389,0.00007945213,0.00004309425],"domain_scores_gemma":[0.9995732,0.0001998316,0.00006151664,0.00003572022,0.00009950931,0.00003028155],"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":[0.0000829312,0.00004132145,0.0005406597,0.00005305187,0.00003764174,0.00007276103,0.00005250085,0.9296806,0.005342796,0.006218492,0.0009398422,0.05693737],"study_design_scores_gemma":[0.000006035279,0.00001931648,0.00003080405,0.000001725376,0.00000360904,0.000009404098,0.000002641362,0.9984921,0.0004234157,0.0007903551,0.0002183916,0.00000224103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008382734,0.000144306,0.9890099,0.0001088945,0.00003090818,0.00001672381,0.00001529991,0.0002575218,0.002033674],"genre_scores_gemma":[0.8226607,0.0002594223,0.1709972,0.0003172288,0.00004205516,0.0001251654,0.00009657969,0.00005974951,0.005441804],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003425166,"threshold_uncertainty_score":0.006810427,"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."}}