{"id":"W2032378315","doi":"10.1109/tcyb.2014.2311578","title":"A Clustering-Based Graph Laplacian Framework for Value Function Approximation in Reinforcement Learning","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Reinforcement learning; Cluster analysis; Graph; Laplace operator; Reinforcement; Laplacian matrix; Computer science; Mathematics; Theoretical computer science; Artificial intelligence; Psychology; Mathematical analysis; Social psychology","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":[0.001080946,0.0008550411,0.001007556,0.0009397635,0.0004501111,0.0009100616,0.001376494,0.0009337438,0.002031742],"category_scores_gemma":[0.003315634,0.0003498407,0.0009115535,0.001225512,0.001003492,0.001292129,0.001034884,0.001657465,0.0004459363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001023706,"about_ca_system_score_gemma":0.001033782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004776283,"about_ca_topic_score_gemma":0.003408422,"domain_scores_codex":[0.999387,0.0002558825,0.00002911784,0.0001206685,0.0001674397,0.00003997946],"domain_scores_gemma":[0.9991609,0.0004573737,0.00007640605,0.0000781139,0.0001846574,0.00004272018],"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":[0.00002841849,0.00004369291,0.0003029499,0.00008858188,0.00004143601,0.00006550713,0.00008135842,0.8134548,0.002594827,0.12955,0.001699663,0.05204867],"study_design_scores_gemma":[0.000001852606,0.000008764056,0.00002566789,0.000002420391,0.000002405544,0.000007894494,0.000003686476,0.9818486,0.0001343798,0.01760281,0.0003574572,0.000004123707],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0013186,0.00009306885,0.9977931,0.00007346578,0.00001479271,0.00001322696,0.00001783013,0.00006115794,0.0006148745],"genre_scores_gemma":[0.4369905,0.0007948863,0.556937,0.0001950749,0.0001201822,0.0002937685,0.0002701611,0.0001451719,0.004253306],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004776283,"threshold_uncertainty_score":0.009496927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0121960861024255,"score_gpt":0.2383362696693834,"score_spread":0.2261401835669579,"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."}}