{"id":"W4410294547","doi":"10.1109/access.2025.3569236","title":"New Approaches for Network Topology Optimization Using Deep Reinforcement Learning and Graph Neural Network","year":2025,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Computing and Algorithms","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"Mitacs","keywords":"Computer science; Reinforcement learning; Network topology; Artificial neural network; Artificial intelligence; Graph; Topology (electrical circuits); Theoretical computer science; Mathematics; Computer network","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0009802819,0.001082098,0.0008698824,0.0008529466,0.0003440907,0.0007982536,0.00160165,0.001046831,0.001409765],"category_scores_gemma":[0.00271528,0.0005235818,0.0005260803,0.0007048676,0.0009680783,0.001545098,0.00121513,0.001538411,0.0002107309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001229224,"about_ca_system_score_gemma":0.0009552044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005193688,"about_ca_topic_score_gemma":0.006865547,"domain_scores_codex":[0.9996834,0.0001108954,0.00001532178,0.00007494568,0.00007589248,0.00003949314],"domain_scores_gemma":[0.9989697,0.0005948347,0.0001488032,0.00008078452,0.0001444743,0.00006144186],"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":[0.00001696262,0.00002638959,0.0002952408,0.00003340111,0.00002419346,0.00002470267,0.00002086366,0.9644724,0.0005501524,0.01000448,0.0006388861,0.02389244],"study_design_scores_gemma":[0.000001817698,0.000005210076,0.00001801778,0.000001446929,0.00000157345,0.000002755122,0.000001906891,0.9966393,0.00005743852,0.003160368,0.0001090347,0.000001148096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009293688,0.0004174541,0.9879876,0.0003043018,0.00004330116,0.00002695889,0.00002961366,0.0002498568,0.001647221],"genre_scores_gemma":[0.7319597,0.0007627478,0.2621363,0.0003519227,0.0001557174,0.0002247446,0.0001820535,0.0001570305,0.004069829],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005193688,"threshold_uncertainty_score":0.01032692,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05907049111675852,"score_gpt":0.3592241498599898,"score_spread":0.3001536587432313,"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."}}