{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000537501,0.001561577,0.0007755078,0.0007895487,0.0002335813,0.001503655,0.0007646377,0.001545259,0.005056627],"category_scores_gemma":[0.0009058538,0.0004866029,0.0008252827,0.001159131,0.0005972534,0.001618553,0.0007385341,0.002796117,0.00251244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000726982,"about_ca_system_score_gemma":0.000681461,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001928432,"about_ca_topic_score_gemma":0.001609928,"domain_scores_codex":[0.9998361,0.00004058492,0.00001498842,0.00003973925,0.00004976392,0.00001873728],"domain_scores_gemma":[0.9997316,0.0001840189,0.00001717393,0.00001105462,0.00003711852,0.00001912811],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000710059,0.0003284614,0.0007234543,0.004105163,0.0001800994,0.0004811573,0.0003424937,0.07477953,0.004639329,0.274514,0.08738671,0.5524486],"study_design_scores_gemma":[0.00002374235,0.0003532692,0.001298812,0.001597494,0.00008895237,0.0007571804,0.0001094644,0.2282873,0.001417094,0.1710053,0.5949572,0.0001041596],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.003230073,0.5505801,0.3910863,0.005130856,0.003927758,0.0001307941,0.0003032901,0.0005971034,0.04501372],"genre_scores_gemma":[0.06884315,0.6815147,0.1700854,0.003101209,0.01241281,0.0005853076,0.0009286514,0.0003353299,0.06219338],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.005056627,"threshold_uncertainty_score":0.0169161,"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."}}