{"id":"W4391020236","doi":"10.1109/tsc.2024.3355937","title":"Hierarchical Deep Reinforcement Learning for Joint Service Caching and Computation Offloading in Mobile Edge-Cloud Computing","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Services Computing","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Chongqing Research Program of Basic Research and Frontier Technology; Chongqing University of Posts and Telecommunications","keywords":"Computer science; Computation offloading; Cloud computing; Reinforcement learning; Distributed computing; Edge computing; Latency (audio); Mobile edge computing; Mobile cloud computing; Enhanced Data Rates for GSM Evolution; Server; Edge device; Computer network; Artificial intelligence","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":[0.001066161,0.0008177652,0.001209767,0.0002855982,0.0004135711,0.0006960774,0.001321747,0.0009567409,0.00141874],"category_scores_gemma":[0.00276941,0.0003863309,0.0003623732,0.0003289137,0.000887347,0.0009219747,0.0009916325,0.001523675,0.000192492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001382872,"about_ca_system_score_gemma":0.002193043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0153804,"about_ca_topic_score_gemma":0.01435763,"domain_scores_codex":[0.9994974,0.0001311169,0.00002025036,0.0001076844,0.00008477721,0.0001586996],"domain_scores_gemma":[0.9989976,0.000583795,0.0001048105,0.00005304219,0.0001673641,0.00009340015],"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":[0.00007220081,0.00006919442,0.0007408566,0.00003208659,0.00002164983,0.0000433884,0.00003256392,0.9731327,0.0007254664,0.0034726,0.0007420566,0.02091534],"study_design_scores_gemma":[0.000003296512,0.000006276392,0.00002519953,0.000001077953,0.000001492015,0.000001845184,0.000002116692,0.999177,0.00006746805,0.0006785476,0.00003460886,9.328596e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07004827,0.0005535721,0.9247777,0.0005545401,0.00007220991,0.00006525812,0.00004945061,0.0006747141,0.003204209],"genre_scores_gemma":[0.9688374,0.0001055189,0.02938828,0.000174837,0.0000240192,0.00005639,0.00004920844,0.00003399499,0.001330394],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0153804,"threshold_uncertainty_score":0.03058171,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01995441115390935,"score_gpt":0.2733401587742251,"score_spread":0.2533857476203157,"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."}}