{"id":"W3116943292","doi":"10.1109/isncc49221.2020.9297353","title":"Resource Management Based on Reinforcement Learning for D2D Communication in Cellular Networks","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced MIMO Systems Optimization","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Reinforcement learning; Computer science; Markov decision process; Cellular network; Latency (audio); Power control; Spectral efficiency; Q-learning; Distributed computing; Wireless network; Computer network; Wireless; Markov process; Channel (broadcasting); Artificial intelligence; Power (physics); Telecommunications","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":[0.0001189428,0.00008736701,0.00009165343,0.00005020978,0.00003876959,0.00001469952,0.0001020209,0.00003872407,0.00002066077],"category_scores_gemma":[0.000009190395,0.00009689671,0.00002299312,0.0001513475,0.000004426048,0.00005206981,0.00002170273,0.0001086397,0.000007502732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000812467,"about_ca_system_score_gemma":0.000001362811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002095851,"about_ca_topic_score_gemma":0.000002023937,"domain_scores_codex":[0.9994693,0.0000238377,0.0002012443,0.0001072978,0.00006320282,0.0001351471],"domain_scores_gemma":[0.9996933,0.00005078394,0.00002866271,0.000181242,0.00001104201,0.0000349274],"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":[0.00001864983,0.000003561831,0.0000302351,0.00007355268,0.000005282107,5.424976e-7,0.00009002182,0.9966975,0.00004732531,0.0007582343,0.0005578571,0.001717268],"study_design_scores_gemma":[0.0005575179,0.00003877057,0.000006907604,0.00005762473,0.00000415458,2.485634e-8,0.0001739946,0.9837089,0.0003562881,0.000005845862,0.01499193,0.00009809314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00008207456,0.00006080725,0.9697205,0.000175432,0.00002139887,0.0005392047,1.323406e-7,0.000236872,0.0291636],"genre_scores_gemma":[0.9790996,0.00002310685,0.02003528,0.0002514844,0.00002491926,0.0001131081,0.00009599099,0.00003103423,0.000325458],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9790176,"threshold_uncertainty_score":0.3951333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01111770541155206,"score_gpt":0.2025312453126293,"score_spread":0.1914135399010773,"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."}}