{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009763584,0.0005454289,0.000821932,0.0002248415,0.0003295109,0.0004668056,0.0009701388,0.0007313047,0.001222973],"category_scores_gemma":[0.002358495,0.0002316067,0.0002700754,0.0003558409,0.0007991944,0.00083912,0.0008750049,0.001241427,0.0001560802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00103309,"about_ca_system_score_gemma":0.001080476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005341594,"about_ca_topic_score_gemma":0.004266796,"domain_scores_codex":[0.9996106,0.0001325576,0.00001605503,0.00006627366,0.0000901959,0.0000843357],"domain_scores_gemma":[0.9988067,0.0007572632,0.0001400136,0.00007733372,0.0001428868,0.00007576153],"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":[0.00005244847,0.00004724954,0.0002687174,0.00002934647,0.00001391668,0.00003053681,0.00001934983,0.9759042,0.0009592318,0.003831884,0.0005716195,0.01827161],"study_design_scores_gemma":[0.000003468677,0.000009655818,0.00002365609,0.000001101085,0.000001477367,0.000003480563,0.000001737866,0.9989048,0.00017787,0.0008102745,0.00006103189,0.00000139884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04736198,0.0006055238,0.9483927,0.0004119069,0.00005748211,0.00003276769,0.00004233589,0.0003188975,0.002776506],"genre_scores_gemma":[0.9736263,0.000149964,0.02482305,0.00009801502,0.00001970922,0.00003461256,0.00003647659,0.00001707743,0.001194729],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005341594,"threshold_uncertainty_score":0.01062101,"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."}}