{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003033472,0.0001720964,0.0001527908,0.00008697021,0.000244208,0.0001571098,0.0008663603,0.00005146189,0.00003868432],"category_scores_gemma":[0.00001769854,0.0001317631,0.00009113047,0.0003471257,0.00009887029,0.0004268622,0.0001278466,0.000271042,0.00003808502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006412333,"about_ca_system_score_gemma":0.00003651695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008951294,"about_ca_topic_score_gemma":0.000003050637,"domain_scores_codex":[0.9983744,0.00001724477,0.0004550687,0.0003174916,0.0005681744,0.0002676395],"domain_scores_gemma":[0.9988362,0.00005709491,0.0003968046,0.0001633344,0.000504512,0.00004202248],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001524422,0.00007200641,0.0003722174,0.000006454325,0.00002268055,0.000001325509,0.0001043268,0.1846826,0.002364161,0.7891507,0.01002641,0.01318192],"study_design_scores_gemma":[0.0002451274,0.0001229051,0.002931553,0.00007349474,0.000006512041,0.00002235889,0.00002523073,0.9615629,0.003095044,0.02872391,0.003023231,0.0001677213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1751654,0.0001640201,0.6664578,0.03264513,0.002831326,0.001375725,0.00001223358,0.0007169637,0.1206314],"genre_scores_gemma":[0.9910769,0.00004104628,0.005392569,0.0002473906,0.0007449196,0.00006174168,0.00001539829,0.000009640066,0.002410349],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8159116,"threshold_uncertainty_score":0.5373143,"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."}}