{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003439841,0.0002456046,0.000249413,0.0001627975,0.0002983552,0.00006123742,0.001540291,0.00008462864,0.0002971806],"category_scores_gemma":[0.0000675553,0.0002769087,0.0000715154,0.0005937252,0.00003425002,0.000143097,0.001398281,0.001319108,0.00007824905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005324094,"about_ca_system_score_gemma":0.00001292395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004267225,"about_ca_topic_score_gemma":0.0000494931,"domain_scores_codex":[0.9985079,0.0001396772,0.0004711038,0.0002673539,0.0002823928,0.0003316357],"domain_scores_gemma":[0.998499,0.0001102942,0.00012623,0.00112162,0.0000739094,0.00006895696],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001537171,0.00002109701,0.0001661385,0.00003859426,0.00005744021,0.000001359403,0.003783842,0.9837555,0.0007060751,0.002675368,0.001579181,0.007200063],"study_design_scores_gemma":[0.0002368663,0.0001218394,0.00006437064,0.00005195174,0.00001315759,0.000028065,0.01730203,0.4865868,0.006817511,0.0002497501,0.4880304,0.0004972843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1116396,0.009737868,0.8297562,0.002192133,0.0009530943,0.001342736,0.00000442431,0.005837617,0.03853631],"genre_scores_gemma":[0.922156,0.0003071121,0.07598907,0.0002140428,0.00004727527,0.0002728771,0.000106536,0.00006682771,0.0008402452],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8105164,"threshold_uncertainty_score":0.9999683,"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."}}