{"id":"W4282966575","doi":"10.1109/icpr56361.2022.9956256","title":"Deep Reinforcement Learning for Exact Combinatorial Optimization: Learning to Branch","year":2022,"lang":"en","type":"article","venue":"2022 26th International Conference on Pattern Recognition (ICPR)","topic":"Auction Theory and Applications","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Combinatorial optimization; Artificial intelligence; Heuristics; Inference; Machine learning; Monte Carlo tree search; Heuristic; Optimization problem; Mathematical optimization; Monte Carlo method; Algorithm; Mathematics","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001905987,0.0002275089,0.0002582176,0.0005250506,0.001231488,0.0003982032,0.0008919155,0.00006480204,0.05809035],"category_scores_gemma":[0.0011765,0.0002391628,0.0001801988,0.0005826266,0.00004695679,0.0003190176,0.0003203571,0.0005677326,0.0009021938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002325371,"about_ca_system_score_gemma":0.00009419386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001458612,"about_ca_topic_score_gemma":0.000004547887,"domain_scores_codex":[0.9960013,0.0004446102,0.000816067,0.0007574887,0.001682543,0.0002979883],"domain_scores_gemma":[0.9973003,0.00070268,0.0005504008,0.0002926994,0.0009852891,0.0001686594],"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":[0.0003720678,0.0001653315,0.0005844952,0.000004189337,0.00005385882,0.000002450511,0.0008228663,0.8403119,0.0002554557,0.01628549,0.00287794,0.1382639],"study_design_scores_gemma":[0.002342608,0.001248934,0.0003580043,0.00003890485,0.00003036453,0.00002522836,0.005588076,0.7936985,0.001092095,0.07050192,0.1243834,0.0006919489],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01497952,0.000005444092,0.9549674,0.004744892,0.003101244,0.0008467782,0.0000833142,0.000137697,0.02113371],"genre_scores_gemma":[0.986951,0.00001214275,0.0004624401,0.001631536,0.0004492587,0.00137207,0.001014044,0.00002999912,0.008077506],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9719715,"threshold_uncertainty_score":0.9998757,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1202884624938102,"score_gpt":0.3655548205745376,"score_spread":0.2452663580807274,"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."}}