{"id":"W3101189765","doi":"10.1109/comst.2021.3063822","title":"Single and Multi-Agent Deep Reinforcement Learning for AI-Enabled Wireless Networks: A Tutorial","year":2021,"lang":"en","type":"preprint","venue":"IEEE Communications Surveys & Tutorials","topic":"Advanced MIMO Systems Optimization","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Scalability; Artificial intelligence; Context (archaeology); Wireless network; Distributed computing; Wireless; Telecommunications","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":[0.002953204,0.0005935088,0.001020743,0.0001916864,0.00049723,0.0004973754,0.0009804136,0.0006627602,0.00001225863],"category_scores_gemma":[0.0007085425,0.0007295776,0.0002080813,0.0002947101,0.0001298961,0.0003252527,0.0008789324,0.0009841856,0.000004383966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007234206,"about_ca_system_score_gemma":0.0001558849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000244387,"about_ca_topic_score_gemma":0.0006706109,"domain_scores_codex":[0.9956463,0.001633533,0.00134559,0.0005884664,0.0002452302,0.0005409053],"domain_scores_gemma":[0.9946034,0.001338849,0.0004948002,0.002571596,0.0008245872,0.0001667685],"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":[0.00001245677,0.00007737085,0.00007071282,0.0003092584,0.0002707861,0.000001012721,0.0009423129,0.9919618,0.002890429,0.0001311525,0.0002232092,0.003109433],"study_design_scores_gemma":[0.001270468,0.00004256828,0.00003321886,0.0004538986,0.0001533702,0.000003119339,0.0002210039,0.9876186,0.0009554267,0.00004396151,0.00845849,0.0007458995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001838101,0.005669523,0.9742137,0.00003937855,0.01523624,0.002186194,0.00002448851,0.0006411206,0.0001513156],"genre_scores_gemma":[0.9425851,0.004376907,0.04572409,0.00001864068,0.002414338,0.001966582,0.002306996,0.0002422684,0.0003650819],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.940747,"threshold_uncertainty_score":0.9995155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04918213408132204,"score_gpt":0.2932754279747203,"score_spread":0.2440932938933983,"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."}}