{"id":"W4317419678","doi":"10.1109/vtc2022-fall57202.2022.10012942","title":"Heterogeneous Mean-Field Multi-Agent Reinforcement Learning for Communication Routing Selection in SAGI-Net","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)","topic":"UAV Applications and Optimization","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Tsinghua Shenzhen International Graduate School; Tsinghua University","keywords":"Reinforcement learning; Computer science; Routing (electronic design automation); Communications system; Distributed computing; Selection (genetic algorithm); Efficient energy use; Field (mathematics); Telecommunications network; Communications satellite; Satellite; Artificial intelligence; Computer network; Mathematics; Electrical engineering; Aerospace 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004734329,0.0002679376,0.0002985839,0.0004906192,0.000605884,0.00005440242,0.0005534042,0.0002519344,0.0001295095],"category_scores_gemma":[0.00006292071,0.0003368708,0.00008750743,0.0009272508,0.00004686167,0.000124268,0.000211109,0.0009843112,0.0000130696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005303452,"about_ca_system_score_gemma":0.00005868798,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002175706,"about_ca_topic_score_gemma":0.0009762432,"domain_scores_codex":[0.9982184,0.00008400875,0.0005530391,0.0004266567,0.0002424036,0.0004755092],"domain_scores_gemma":[0.9991295,0.00007056369,0.0001712438,0.0004601477,0.0001192052,0.00004931171],"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":[0.00001674522,0.00007006646,0.002055707,0.00002985082,0.0000579726,0.000003357989,0.0004539739,0.9759251,0.01139536,0.002710714,0.000137508,0.007143642],"study_design_scores_gemma":[0.0008122262,0.0002060992,0.0001127267,0.00002443655,0.00003384646,0.00002492853,0.0009525567,0.9816651,0.008550391,0.0003542795,0.00690743,0.0003559418],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3968886,0.0005197289,0.5994254,0.0005085994,0.0001902756,0.001297079,0.000008530872,0.0009008528,0.0002609618],"genre_scores_gemma":[0.9901114,0.0003454599,0.006721362,0.00009889114,0.00002124103,0.00222856,0.0002028102,0.00005845854,0.0002118563],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5932228,"threshold_uncertainty_score":0.9999083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01490423555588995,"score_gpt":0.2346709295781379,"score_spread":0.219766694022248,"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."}}