{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004163533,0.001353309,0.001944449,0.0006870073,0.0005828917,0.001134623,0.002373741,0.001838744,0.004191409],"category_scores_gemma":[0.01448324,0.0006964311,0.0006027406,0.0005868663,0.002009049,0.001759668,0.00158728,0.00282885,0.0007385939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001407765,"about_ca_system_score_gemma":0.001315198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00257617,"about_ca_topic_score_gemma":0.002582131,"domain_scores_codex":[0.9984836,0.0008149971,0.0000659093,0.0002194307,0.0002865072,0.0001295744],"domain_scores_gemma":[0.9908936,0.007339269,0.0004509765,0.0004258706,0.0006340723,0.0002561991],"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":[0.0001382313,0.0001357906,0.000739051,0.0001045639,0.00006094804,0.00009188858,0.0000812524,0.8906666,0.0007697589,0.05137312,0.001946949,0.05389189],"study_design_scores_gemma":[0.00001954732,0.00002098162,0.0000252783,0.000005879429,0.000003964396,0.000007920907,0.000003140684,0.9877176,0.0001666701,0.01174339,0.0002821379,0.000003392267],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007511758,0.0003179684,0.9893056,0.0003590946,0.00005124995,0.0000642865,0.00002618185,0.0003162895,0.002047604],"genre_scores_gemma":[0.8150852,0.0003797262,0.1783703,0.0004735206,0.0001599768,0.0006348022,0.0001525713,0.0001222552,0.004621635],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004191409,"threshold_uncertainty_score":0.02201915,"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."}}