{"id":"W2907002301","doi":"10.1109/wimob.2018.8589114","title":"Deep Reinforcement Learning-based Data Transmission for D2D Communications","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced MIMO Systems Optimization","field":"Engineering","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Reinforcement learning; Transmission (telecommunications); Base station; Interference (communication); Markov chain; Computer network; Wireless network; Markov decision process; Cellular network; Wireless; Telecommunications link; Markov process; Distributed computing; Artificial intelligence; Channel (broadcasting); Telecommunications; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.0001122509,0.00007551345,0.00007536049,0.00003935866,0.0001269433,0.00001480616,0.0003981796,0.00004100012,0.00009802391],"category_scores_gemma":[0.00001349869,0.0000732226,0.00001618762,0.00008629523,0.00002892638,0.0001685564,0.00004049102,0.00005557636,0.00003044429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003503701,"about_ca_system_score_gemma":0.00001061662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006410431,"about_ca_topic_score_gemma":0.00003165017,"domain_scores_codex":[0.9995299,0.00001209292,0.0001749755,0.0001090347,0.00005126036,0.0001227136],"domain_scores_gemma":[0.9989374,0.00006138681,0.00002306526,0.0008721096,0.00006572535,0.00004031322],"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":[0.000005413262,0.000005807431,0.000007930948,0.00003534124,0.000008477786,2.438076e-8,0.00008275296,0.9847276,0.0006793533,0.0001952241,0.00104877,0.01320336],"study_design_scores_gemma":[0.0002866829,0.00003788785,0.000001449452,0.00001920691,0.000008134746,2.48538e-7,0.00003224679,0.8736595,0.001824126,0.00001836736,0.1240297,0.00008243114],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000007168667,0.0001171517,0.9916189,0.0001054735,0.00005910243,0.0003326786,0.000001927615,0.0003701787,0.007387473],"genre_scores_gemma":[0.698074,0.00004080157,0.3004195,0.0000410403,0.0000544814,0.00005054601,0.000634065,0.00003176694,0.0006538114],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6980668,"threshold_uncertainty_score":0.2985931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04010985785049623,"score_gpt":0.2933176738377501,"score_spread":0.2532078159872538,"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."}}