{"id":"W4246584857","doi":"10.1109/ijcnn.2006.1716072","title":"Aggregation of Reinforcement Learning Algorithms","year":2006,"lang":"en","type":"article","venue":"The 2006 IEEE International Joint Conference on Neural Network Proceedings","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Learning classifier system; Instance-based learning; Machine learning; Robustness (evolution); Robot learning; Algorithm; Online machine learning; Unsupervised learning; Computational learning theory; Proactive learning; Robot; Mobile robot","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":[0.002471974,0.001050199,0.001625178,0.0007534099,0.0004821247,0.001144005,0.001340825,0.0008166509,0.002462299],"category_scores_gemma":[0.006298091,0.0004046377,0.0007065103,0.0005961248,0.0007344641,0.001291509,0.001724893,0.00131174,0.0004793582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007906887,"about_ca_system_score_gemma":0.0008316963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001868693,"about_ca_topic_score_gemma":0.001390104,"domain_scores_codex":[0.998396,0.0005053342,0.0001317347,0.0003341451,0.000455443,0.0001773004],"domain_scores_gemma":[0.9969975,0.001411071,0.0003171483,0.0004692752,0.0006416349,0.000163458],"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":[0.0001611425,0.0001453269,0.001718658,0.000137958,0.0001647179,0.0001132958,0.0001268986,0.7827545,0.002927013,0.01462067,0.001526689,0.1956032],"study_design_scores_gemma":[0.00002371944,0.00008040322,0.0001616181,0.000009753989,0.00001921604,0.00003231777,0.000009357356,0.9908336,0.0008498369,0.006859069,0.00111398,0.000007174145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02797537,0.0005272459,0.9662473,0.0001603837,0.0001050651,0.000117423,0.00002560551,0.0009357086,0.003905954],"genre_scores_gemma":[0.8327594,0.0003413885,0.1633245,0.0001351676,0.00009261077,0.0002433803,0.00008178712,0.00007766206,0.002944117],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002471974,"threshold_uncertainty_score":0.01307315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03150880397224771,"score_gpt":0.2575689761526512,"score_spread":0.2260601721804035,"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."}}