{"id":"W1998314229","doi":"10.1145/1089827.1089829","title":"Reinforcement learning for active model selection","year":2005,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Markov decision process; Artificial intelligence; Machine learning; Learning classifier system; Classifier (UML); Feature selection; Selection (genetic algorithm); Training set; Feature (linguistics); Active learning (machine learning); Markov process; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001795588,0.0001109303,0.00009471399,0.00008854566,0.0002122985,0.0001097119,0.000344406,0.00005005198,0.00003329236],"category_scores_gemma":[0.00006133135,0.0001054719,0.00005998846,0.0001649725,0.00001123978,0.0007378939,0.000108401,0.0001458023,0.0000732569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001476961,"about_ca_system_score_gemma":0.00006130493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000426319,"about_ca_topic_score_gemma":0.000002452773,"domain_scores_codex":[0.9990309,0.00001507928,0.0001939482,0.0002435643,0.000223054,0.0002933772],"domain_scores_gemma":[0.9994892,0.00006118922,0.00009400239,0.0001796183,0.0001168098,0.00005918847],"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":[0.000006577837,0.000005814331,0.00001894812,0.000003774569,0.00001104137,4.26461e-8,0.0002982314,0.9300838,0.0003929502,0.05323589,0.0007576233,0.01518535],"study_design_scores_gemma":[0.0003081999,0.0001387762,0.0000175781,0.000004131383,0.000004218291,0.000001697957,0.00001602159,0.9789624,0.006806335,0.0002171855,0.01338675,0.000136684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002859446,0.000002768598,0.9736742,0.0006209681,0.00006655906,0.0002559391,3.6686e-8,0.0003351074,0.02475852],"genre_scores_gemma":[0.6680903,0.000004554598,0.3007622,0.0003850129,0.00007485474,0.00003715068,0.00000322226,0.000009055167,0.03063366],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6729119,"threshold_uncertainty_score":0.430102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02332588564199617,"score_gpt":0.2704950962549127,"score_spread":0.2471692106129166,"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."}}