{"id":"W4417201803","doi":"10.1109/tvt.2025.3642703","title":"Counterfactual Multi-Agent DRL for Efficient Task Offloading in Vehicular Edge Computing","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Vehicular Technology","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Counterfactual thinking; Reinforcement learning; Markov decision process; Latency (audio); Scheduling (production processes); Edge computing; Task (project management); Task analysis; Enhanced Data Rates for GSM Evolution","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":[0.002626169,0.0007564347,0.001005011,0.0003913137,0.0005362253,0.001081082,0.001729626,0.0007927309,0.001200431],"category_scores_gemma":[0.005456554,0.0004564209,0.000426741,0.0003932383,0.001254377,0.001383,0.001519178,0.001286691,0.0001447569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001185415,"about_ca_system_score_gemma":0.00191527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006045829,"about_ca_topic_score_gemma":0.00639558,"domain_scores_codex":[0.9989334,0.0004652895,0.00004585197,0.0001958526,0.0001690002,0.0001906678],"domain_scores_gemma":[0.9972415,0.001639168,0.0003810903,0.000245252,0.0002723205,0.0002205712],"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":[0.00008977197,0.00003966915,0.0005149793,0.00002943197,0.0000191828,0.00004992314,0.0000377101,0.9808413,0.0008434572,0.005840065,0.0002798967,0.01141469],"study_design_scores_gemma":[0.000005644723,0.00001294538,0.00003300311,0.000001304523,0.000002180525,0.000003995012,0.000004666013,0.9976272,0.0001356375,0.00209517,0.00007650136,0.00000180992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05223501,0.0003320194,0.9448239,0.0003540004,0.0000711511,0.00006902405,0.00003322893,0.0003405028,0.001741187],"genre_scores_gemma":[0.9632003,0.00006841644,0.03584642,0.0001211006,0.00001940758,0.00005902458,0.0000273338,0.00002518499,0.0006328042],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006045829,"threshold_uncertainty_score":0.01388866,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01721799770839729,"score_gpt":0.2704073064692964,"score_spread":0.2531893087608992,"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."}}