{"id":"W4388505095","doi":"10.1109/lcomm.2023.3331216","title":"Deep Recurrent Reinforcement Learning for Partially Observable User Association in a Vertical Heterogenous Network","year":2023,"lang":"en","type":"article","venue":"IEEE Communications Letters","topic":"Advanced MIMO Systems Optimization","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Reinforcement learning; Base station; Scalability; Association (psychology); Wireless network; Computer network; Deep learning; Channel state information; Wireless; Distributed computing; Artificial intelligence; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001089201,0.0005554818,0.0009406001,0.0001795992,0.0003139835,0.0005259301,0.001067518,0.0008290156,0.001320054],"category_scores_gemma":[0.003021043,0.0004395946,0.0003020303,0.0002426808,0.0008767123,0.00095499,0.0008687046,0.001219998,0.0001534059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009629683,"about_ca_system_score_gemma":0.0009633679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01184859,"about_ca_topic_score_gemma":0.01091527,"domain_scores_codex":[0.999661,0.0001242905,0.00001134441,0.00007523674,0.00004555157,0.00008267665],"domain_scores_gemma":[0.9987047,0.0008310133,0.0001568896,0.00006725362,0.0001519322,0.00008822854],"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":[0.00006153333,0.00002175821,0.000479061,0.00001221827,0.00001450698,0.00005191167,0.00002329871,0.9889984,0.0004710428,0.003093341,0.0002876435,0.006485353],"study_design_scores_gemma":[0.000002247369,0.000004896249,0.00002495857,5.548466e-7,0.000001034149,0.000002027639,0.000001484112,0.9991947,0.00004484816,0.0007003408,0.00002212382,7.199694e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1703955,0.0003811211,0.824712,0.0006547141,0.00007487149,0.00003693549,0.00007675988,0.0004332413,0.003234771],"genre_scores_gemma":[0.9814859,0.00006201479,0.01651326,0.00008277441,0.00001457296,0.00002460174,0.00004146212,0.0000172353,0.001758131],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01184859,"threshold_uncertainty_score":0.02355927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03345750505697552,"score_gpt":0.2652852761680216,"score_spread":0.231827771111046,"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."}}