{"id":"W4293525376","doi":"10.3390/fi14090256","title":"Intelligent Reflecting Surface-Aided Device-to-Device Communication: A Deep Reinforcement Learning Approach","year":2022,"lang":"en","type":"article","venue":"Future Internet","topic":"Advanced Wireless Communication Technologies","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Reinforcement learning; Computer science; Underlay; Markov decision process; Scalability; Wireless network; Transmitter power output; Wireless; Optimization problem; Distributed computing; Mathematical optimization; Computer network; Artificial intelligence; Telecommunications; Transmitter; Markov process; Algorithm; Signal-to-noise ratio (imaging)","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":[0.0008794524,0.000847651,0.001222815,0.000325321,0.0003148516,0.0008311305,0.001356114,0.001362392,0.001893393],"category_scores_gemma":[0.001751858,0.0004990046,0.0005394228,0.0003903208,0.001010941,0.0007815784,0.001086788,0.001660002,0.0002175645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009587507,"about_ca_system_score_gemma":0.00126995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01120683,"about_ca_topic_score_gemma":0.006424893,"domain_scores_codex":[0.9996839,0.00009059166,0.00001486627,0.00007055084,0.00006444159,0.00007562325],"domain_scores_gemma":[0.9992096,0.0004817825,0.00008552431,0.0000308588,0.0001383398,0.00005381465],"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":[0.00002772502,0.00002916974,0.0003889658,0.00002974359,0.00002235187,0.00005446824,0.00002945383,0.9819875,0.0004541971,0.004818525,0.0004145752,0.01174314],"study_design_scores_gemma":[0.000002195257,0.000006215362,0.00001736862,0.000001552802,0.000001975793,0.000002026615,0.000001535174,0.9992191,0.00003818054,0.0006488865,0.00005971976,0.000001128639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03081406,0.0008136561,0.9625072,0.0006339453,0.00007723038,0.00003513143,0.00003986824,0.0002854976,0.004793453],"genre_scores_gemma":[0.9578756,0.0003331007,0.03780314,0.0002246152,0.0000481934,0.00009367675,0.0000675081,0.00003105614,0.003523061],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01120683,"threshold_uncertainty_score":0.0222832,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03234723496940389,"score_gpt":0.2837737932649364,"score_spread":0.2514265582955325,"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."}}