{"id":"W4409475416","doi":"10.1109/iceaai64185.2025.10956500","title":"Enhanced Task Offloading in Mobile Edge Computing: A Hybrid Approach Using Deep Q-Learning from Demonstrations and Heuristic Optimization","year":2025,"lang":"en","type":"article","venue":"","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Computer science; Mobile edge computing; Heuristic; Task (project management); Edge computing; Enhanced Data Rates for GSM Evolution; Artificial intelligence; Deep learning; Mobile computing; Human–computer interaction; Multimedia; Distributed computing; Computer architecture; Computer network; Engineering; Systems engineering","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":[0.0008334352,0.0006828689,0.0009070211,0.0003601633,0.0002821629,0.0006430948,0.001491998,0.0009040052,0.001628205],"category_scores_gemma":[0.002411816,0.0003839523,0.0003520021,0.0003628875,0.0007550548,0.0009759701,0.001015946,0.0009792597,0.0001520091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006699839,"about_ca_system_score_gemma":0.001360155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006590122,"about_ca_topic_score_gemma":0.006219536,"domain_scores_codex":[0.999737,0.00006556709,0.00001480694,0.00006741938,0.00004825015,0.00006703075],"domain_scores_gemma":[0.998968,0.0006235016,0.0001038233,0.00007055426,0.0001411421,0.00009300141],"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":[0.0000698482,0.0001158888,0.0007405255,0.00004883208,0.00002174107,0.00006799547,0.00003990921,0.955374,0.001562047,0.002697436,0.000476047,0.03878577],"study_design_scores_gemma":[0.000005377456,0.00001713299,0.00004072733,0.000001739615,0.000001988722,0.000004079367,0.000003041466,0.9990067,0.0001470326,0.0007094489,0.000061149,0.00000166698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06852728,0.0003598632,0.9273988,0.000353443,0.00005564782,0.00007529809,0.00003745836,0.0004535958,0.002738542],"genre_scores_gemma":[0.9383081,0.000123196,0.05977171,0.000159704,0.00002324739,0.00009503304,0.00004628396,0.00003343572,0.001439334],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006590122,"threshold_uncertainty_score":0.01310354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01286894533095998,"score_gpt":0.2420913958191599,"score_spread":0.2292224504881999,"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."}}