{"id":"W3035018164","doi":"10.1109/twc.2020.3003719","title":"Multi-Agent Reinforcement Learning for Adaptive User Association in Dynamic mmWave Networks","year":2020,"lang":"en","type":"preprint","venue":"IEEE Transactions on Wireless Communications","topic":"Millimeter-Wave Propagation and Modeling","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Scalability; Distributed computing; Overhead (engineering); Context (archaeology); Information exchange; Association (psychology); State (computer science); Computer network; Artificial intelligence; Telecommunications; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"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"],"consensus_categories":[],"category_scores_codex":[0.0003517082,0.0003873787,0.0004464113,0.0003117407,0.0003361217,0.00009180083,0.0006449214,0.000454702,0.00002160166],"category_scores_gemma":[0.00001687218,0.0004883304,0.0002826357,0.0002620731,0.00003325893,0.0001123156,0.00002885161,0.002198028,0.00002529924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001394008,"about_ca_system_score_gemma":0.00007567372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007627356,"about_ca_topic_score_gemma":0.0009013605,"domain_scores_codex":[0.9980419,0.0002000857,0.0007703653,0.0003854549,0.0002322553,0.0003699345],"domain_scores_gemma":[0.9980832,0.0003794494,0.0002336684,0.001000488,0.000186327,0.0001168642],"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":[0.00002217582,0.00009745931,0.00000635057,0.00007997037,0.0002129798,3.376229e-7,0.000921202,0.9880964,0.001308193,0.00002012131,0.00003925043,0.009195541],"study_design_scores_gemma":[0.0007251056,0.00004687939,0.00003909296,0.0002784584,0.0001139878,3.999056e-7,0.0002062953,0.9963938,0.001312397,0.00004493893,0.0004085978,0.000430067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002204554,0.0003158358,0.994168,0.0004868194,0.0006644204,0.001468598,0.00006887146,0.000468262,0.000154593],"genre_scores_gemma":[0.9708523,0.004890294,0.021639,0.00009893238,0.00002805402,0.00167322,0.0003314483,0.0001150044,0.0003718216],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9725291,"threshold_uncertainty_score":0.9997568,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05430455140650424,"score_gpt":0.2785118507762379,"score_spread":0.2242072993697337,"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."}}