{"id":"W2143680741","doi":"10.1109/ijcnn.2006.246661","title":"Aggregation of Reinforcement Learning Algorithms","year":2006,"lang":"en","type":"article","venue":"The 2006 IEEE International Joint Conference on Neural Network Proceedings","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":9,"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; Online machine learning; Unsupervised learning; Algorithm; Proactive learning; Computational learning theory; 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":[0.00258204,0.001101887,0.001701934,0.0007760969,0.000488284,0.001166701,0.001371693,0.0008411498,0.002528564],"category_scores_gemma":[0.006537667,0.0004263474,0.0007347847,0.0006037819,0.0007773601,0.001353065,0.001822088,0.001418802,0.0005085795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008183784,"about_ca_system_score_gemma":0.0008688544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001856568,"about_ca_topic_score_gemma":0.00138193,"domain_scores_codex":[0.9983014,0.0005140507,0.0001472439,0.0003587816,0.0004923704,0.0001862548],"domain_scores_gemma":[0.9967891,0.001515049,0.0003327738,0.0005007284,0.000690496,0.0001718149],"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":[0.0001666998,0.0001444514,0.001624505,0.0001468595,0.0001627429,0.0001062278,0.0001251604,0.775465,0.002958669,0.01447253,0.001519286,0.2031078],"study_design_scores_gemma":[0.0000235757,0.00008085779,0.0001545391,0.00001017675,0.00001867645,0.00003228811,0.000009376013,0.9906357,0.0009099469,0.007021691,0.001095734,0.000007433813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02370398,0.0004869872,0.9711733,0.0001454901,0.00009467905,0.0001142859,0.00002341438,0.0008851622,0.003372702],"genre_scores_gemma":[0.8213934,0.0003627514,0.174576,0.0001416171,0.00009823667,0.0002674019,0.0000845004,0.00008434324,0.002991758],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00258204,"threshold_uncertainty_score":0.0136553,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03689572284387754,"score_gpt":0.2604671221146379,"score_spread":0.2235713992707604,"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."}}