{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006832156,0.0001567949,0.0002240485,0.0002260179,0.00009838366,0.0003675734,0.0007609517,0.00004802071,0.000003311907],"category_scores_gemma":[0.00008610764,0.0001507275,0.00006488714,0.0001714091,0.00002973302,0.0001792656,0.0002388892,0.0006853827,0.000005043282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000839939,"about_ca_system_score_gemma":0.00003534772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002556193,"about_ca_topic_score_gemma":4.878744e-7,"domain_scores_codex":[0.9981614,0.0002297774,0.0005702699,0.0002289089,0.0005822575,0.0002273425],"domain_scores_gemma":[0.9990246,0.0001638254,0.0003735218,0.00008981913,0.0001820402,0.0001661343],"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":[0.00005249138,0.00006949761,0.01533403,0.00004554487,0.00006909033,0.0002653299,0.002675061,0.9215851,0.0001059973,0.0005870284,0.0002041044,0.05900671],"study_design_scores_gemma":[0.0009532537,0.0005523323,0.001385665,0.0001807358,0.00001089133,0.00006431514,0.0002380104,0.9337588,0.00004828902,0.00002429415,0.06262891,0.0001545019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.388268,0.002078159,0.6011418,0.00216226,0.003492167,0.0002241418,2.615209e-7,0.0001407381,0.002492576],"genre_scores_gemma":[0.9951427,0.00006274051,0.003321309,0.000360654,0.001001272,0.000001051397,0.000005584589,0.00001446256,0.00009024271],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6068747,"threshold_uncertainty_score":0.6146488,"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."}}