{"id":"W2156760524","doi":"10.1109/ijcnn.1999.833417","title":"Adaptive exploration in reinforcement learning","year":2003,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Implementation; Artificial intelligence; Connectionism; Machine learning; Reinforcement; Learning classifier system; Artificial neural network; Engineering; Software engineering","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":[0.0003725181,0.00009110331,0.00008608391,0.0001286319,0.00006593943,0.00008711098,0.0002473037,0.00003557065,0.00007313519],"category_scores_gemma":[0.00009589735,0.00008723723,0.00001888858,0.0003735603,0.00001245517,0.0009163018,0.00006769198,0.0001712351,0.000192207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008040226,"about_ca_system_score_gemma":0.00004451842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001499431,"about_ca_topic_score_gemma":0.000004483326,"domain_scores_codex":[0.999006,0.00009740243,0.0002239208,0.0002020161,0.000242121,0.0002285161],"domain_scores_gemma":[0.9995589,0.00005297191,0.00006911222,0.0002361147,0.00004068462,0.00004224348],"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":[8.828794e-7,0.000003810648,0.0003726314,0.000001041699,0.000001865627,0.000002407272,0.0004403448,0.7372749,0.00003744638,0.2609458,0.00004905744,0.0008698417],"study_design_scores_gemma":[0.0002828013,0.0001788445,0.0001600539,0.0000107331,8.2414e-7,0.000001877192,0.0002474098,0.9912731,0.001190374,0.0009822652,0.00553528,0.0001364471],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002576975,0.000008717811,0.8748337,0.000100933,0.0001150012,0.0001128153,3.223448e-9,0.0001099233,0.1244612],"genre_scores_gemma":[0.9425653,0.00001314855,0.05075844,0.0001447472,0.000007485241,0.00001479125,9.546239e-7,0.000005259278,0.006489839],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9423077,"threshold_uncertainty_score":0.3557431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03664087277169577,"score_gpt":0.2510125592442868,"score_spread":0.214371686472591,"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."}}