{"id":"W4307814556","doi":"10.1016/j.neunet.2022.10.022","title":"Reinforcement learning for automatic quadrilateral mesh generation: A soft actor–critic approach","year":2022,"lang":"en","type":"article","venue":"Neural Networks","topic":"Computational Geometry and Mesh Generation","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Reinforcement learning; Mesh generation; Scalability; Artificial intelligence; Markov decision process; Software; Machine learning; Finite element method; Markov process","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003467654,0.0001457409,0.0001493016,0.00009832487,0.0008496837,0.0002240787,0.0003867765,0.00003607736,0.00006126463],"category_scores_gemma":[0.00002647969,0.0001527477,0.000100411,0.0004228229,0.00001328248,0.000353034,0.0002414696,0.0002490299,0.000002223674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008315845,"about_ca_system_score_gemma":0.00004401541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000292191,"about_ca_topic_score_gemma":8.580164e-7,"domain_scores_codex":[0.9985162,0.0001493753,0.0002965744,0.0003720591,0.000351024,0.0003147903],"domain_scores_gemma":[0.9994081,0.0001180551,0.0001044618,0.000220493,0.00007228845,0.00007663904],"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":[0.000005586242,0.0000269643,0.00002557789,0.0000104308,0.00001143644,0.000001994866,0.000219713,0.9597955,0.0001234937,0.006466084,0.003066964,0.03024623],"study_design_scores_gemma":[0.0003523658,0.0002316714,0.00008910177,0.000001977465,0.000008492107,0.00003728814,0.0000165838,0.9944897,0.00003391313,0.0002171548,0.004347051,0.0001747416],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01750637,0.0001474449,0.9798288,0.0005715915,0.00115698,0.0004182976,6.661714e-7,0.0002028046,0.0001670716],"genre_scores_gemma":[0.9818912,0.000002420025,0.01491409,0.0009919098,0.0006765089,0.0003535318,0.0002103526,0.00001237122,0.0009475896],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9649147,"threshold_uncertainty_score":0.6535166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02866328610595497,"score_gpt":0.2520052945808472,"score_spread":0.2233420084748922,"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."}}