{"id":"W4386766554","doi":"10.1109/tmc.2023.3315961","title":"Multi-Agent Deep Reinforcement Learning to Enable Dynamic TDD in a Multi-Cell Environment","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Mobile Computing","topic":"Distributed Control Multi-Agent Systems","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Reinforcement learning; Computer science; Distributed computing; Human–computer interaction; Artificial intelligence","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000794035,0.0003992423,0.0004101362,0.0006556116,0.0004489721,0.0002011758,0.0009140093,0.0001251293,0.00003017106],"category_scores_gemma":[0.00001232112,0.0004450388,0.0001968862,0.00116158,0.00002776895,0.0002556888,0.00004463868,0.0005526485,0.001783805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000769208,"about_ca_system_score_gemma":0.0000545633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001638868,"about_ca_topic_score_gemma":0.00006983252,"domain_scores_codex":[0.9964287,0.0002423743,0.00079696,0.0009928624,0.0005571799,0.0009818797],"domain_scores_gemma":[0.9984648,0.0002329048,0.0001850429,0.0007911131,0.00004589533,0.000280275],"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":[0.000009372938,0.0003529598,0.00005052887,0.00003534137,0.00002577051,0.00004766084,0.002189677,0.9557706,0.00995981,0.000003420579,0.00001512473,0.03153981],"study_design_scores_gemma":[0.002167555,0.0002280785,0.0003493422,0.0001047091,0.00001143669,0.000005773795,0.0006219303,0.9912024,0.003744815,0.000001458509,0.001133858,0.0004286231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03962503,0.00006139501,0.9570525,0.00008397776,0.0009690681,0.001469205,0.000004558968,0.0006836396,0.0000506528],"genre_scores_gemma":[0.9784169,0.00003231073,0.01948368,0.0001058639,0.00002092991,0.0004049561,0.00001090889,0.00004537488,0.00147913],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9387918,"threshold_uncertainty_score":0.9998001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01964898280470179,"score_gpt":0.2545781797765407,"score_spread":0.2349291969718389,"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."}}