{"id":"W3005624551","doi":"10.1007/s13042-020-01077-8","title":"An actor-critic reinforcement learning-based resource management in mobile edge computing systems","year":2020,"lang":"en","type":"article","venue":"International Journal of Machine Learning and Cybernetics","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Reinforcement learning; Markov decision process; Computer science; Mobile edge computing; Mathematical optimization; Wireless; Computational intelligence; Bellman equation; Field (mathematics); Process (computing); Parameterized complexity; Enhanced Data Rates for GSM Evolution; Distributed computing; Markov process; Artificial intelligence; Algorithm; Mathematics","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":[0.001258086,0.0006238531,0.001183295,0.0002941004,0.0005377277,0.001046148,0.001412657,0.001093919,0.002106588],"category_scores_gemma":[0.002115073,0.000338245,0.0003119064,0.0003219217,0.0006383653,0.0007424247,0.0009838627,0.001113404,0.0002449999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008409395,"about_ca_system_score_gemma":0.001351502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008954222,"about_ca_topic_score_gemma":0.006583304,"domain_scores_codex":[0.9994615,0.0001831847,0.00002282112,0.0001325735,0.00008832656,0.0001115666],"domain_scores_gemma":[0.9990945,0.0004811794,0.00007257961,0.0000357487,0.000228621,0.00008736298],"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":[0.0001492404,0.00008027127,0.0005634074,0.00005563231,0.00004509226,0.0001101288,0.00004677304,0.9703429,0.001565619,0.004147145,0.001343419,0.02155026],"study_design_scores_gemma":[0.000005863397,0.00001421257,0.00003381906,0.000002361873,0.000003769464,0.000005659024,0.000003067494,0.9993814,0.00009922718,0.0003702035,0.00007868876,0.000001686106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06303714,0.000864643,0.9263003,0.0007872642,0.0002364145,0.0001274637,0.00004589425,0.0004255648,0.008175245],"genre_scores_gemma":[0.9759294,0.000121061,0.02134368,0.0001278914,0.00003620859,0.00004904903,0.00002247777,0.00002304739,0.002347139],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008954222,"threshold_uncertainty_score":0.01780421,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01088784383653598,"score_gpt":0.2677960930459866,"score_spread":0.2569082492094507,"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."}}