{"id":"W2244307845","doi":"10.1109/ictai.2015.135","title":"RLBS: An Adaptive Backtracking Strategy Based on Reinforcement Learning for Combinatorial Optimization","year":2015,"lang":"en","type":"article","venue":"","topic":"Constraint Satisfaction and Optimization","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Backtracking; Reinforcement learning; Computer science; Mathematical optimization; Iterative deepening depth-first search; Search tree; Combinatorial search; Search algorithm; Scheduling (production processes); Beam stack search; Beam search; Binary number; Combinatorial optimization; Artificial intelligence; Algorithm; Mathematics; Best-first search","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":[0.00036377,0.0001171968,0.0001011727,0.00009105213,0.0001438739,0.0002145525,0.0001830322,0.00006339817,0.0000702075],"category_scores_gemma":[0.00008387487,0.0001144553,0.0000364476,0.0001933773,0.00001768795,0.0007387661,0.00002372911,0.00009218203,0.000009519216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000108973,"about_ca_system_score_gemma":0.0001940471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000164538,"about_ca_topic_score_gemma":0.00000489535,"domain_scores_codex":[0.9989982,0.00007581634,0.0002011282,0.0002788828,0.0002696485,0.0001763451],"domain_scores_gemma":[0.9991829,0.00007892356,0.0001045371,0.0001991655,0.0002906028,0.0001439182],"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":[0.00005344883,0.00002965251,0.00003948277,0.000001617259,0.000003375491,4.47798e-7,0.00009760082,0.9029486,0.000004627344,0.08595472,0.0001063131,0.01076011],"study_design_scores_gemma":[0.001451703,0.001284449,0.00003968897,0.000009267948,0.000003771809,8.141386e-7,0.0001730255,0.9958035,0.0002001293,0.0006021824,0.0002808076,0.000150627],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001131626,0.000001653655,0.9859843,0.0001706949,0.0005692561,0.0003255618,3.914358e-7,0.0002348809,0.01260007],"genre_scores_gemma":[0.8094997,9.380823e-7,0.1899929,0.0002138113,0.00007179785,0.00002331634,0.00003684342,0.000008638312,0.0001520793],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8093866,"threshold_uncertainty_score":0.4667351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05122607948455666,"score_gpt":0.2803174550396211,"score_spread":0.2290913755550644,"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."}}