{"id":"W2963772421","doi":"10.1609/aaai.v33i01.33011443","title":"Improving Optimization Bounds Using Machine Learning: Decision Diagrams Meet Deep Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Bounding overwatch; Reinforcement learning; Computer science; Maximum cut; Mathematical optimization; Set (abstract data type); Relaxation (psychology); Perspective (graphical); Optimization problem; Function (biology); Artificial intelligence; Algorithm; Mathematics; Theoretical computer science","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":[],"consensus_categories":[],"category_scores_codex":[0.001233394,0.0001841858,0.0001826817,0.000186864,0.0003102681,0.000399566,0.0006075448,0.0001018168,0.0001446441],"category_scores_gemma":[0.0004553164,0.0001687237,0.00006705296,0.0005317491,0.00002302718,0.0013831,0.0004279585,0.0002672643,0.00006525558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001882122,"about_ca_system_score_gemma":0.00004763129,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001441983,"about_ca_topic_score_gemma":0.000006760665,"domain_scores_codex":[0.9981137,0.0001779395,0.0004133152,0.0004661198,0.0004800678,0.0003488606],"domain_scores_gemma":[0.9988145,0.0001369513,0.000292913,0.0005258525,0.0001380919,0.00009170676],"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":[0.00001037278,0.00001131075,0.002613998,0.00001221749,0.000005663387,6.751133e-7,0.0002414964,0.938189,0.002237259,0.01284377,0.000001774833,0.04383247],"study_design_scores_gemma":[0.0003218031,0.000179991,0.0001073039,0.00002230041,0.000006107243,0.00001030344,0.00004634189,0.9951355,0.003196839,0.0001589675,0.0005893793,0.0002251658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02114157,0.00006105649,0.9746246,0.00002212492,0.0005705187,0.0002725716,3.853649e-8,0.0003237929,0.002983729],"genre_scores_gemma":[0.3468237,0.00001436151,0.6525167,0.00005160514,0.00002732729,0.000005056117,0.000006576443,0.00001470355,0.0005400296],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3256821,"threshold_uncertainty_score":0.6880352,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01918668479734871,"score_gpt":0.2741466304740873,"score_spread":0.2549599456767386,"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."}}