{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004588389,0.0001892844,0.0001809565,0.000285427,0.0001804345,0.000110527,0.0003110017,0.0001491714,0.000004250354],"category_scores_gemma":[0.0000416848,0.0002070248,0.0001022636,0.0004041345,0.00003986378,0.0001733783,0.000002705304,0.0003778372,0.00001487952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001410071,"about_ca_system_score_gemma":0.00003978191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002977621,"about_ca_topic_score_gemma":0.0001210644,"domain_scores_codex":[0.998575,0.0001169003,0.0003192964,0.0003834724,0.0002681226,0.0003372],"domain_scores_gemma":[0.9989289,0.0004024737,0.0001295392,0.0003837344,0.00008021521,0.00007513063],"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":[0.00007460607,0.00007952553,0.00001136166,0.00002223915,0.00001430939,3.346423e-7,0.0002103877,0.8795409,0.0001002978,0.02200549,0.000002848114,0.09793777],"study_design_scores_gemma":[0.001046869,0.000807424,0.0001072142,0.00007554243,0.00002150268,9.767749e-7,0.00001796893,0.9878755,0.0005674595,0.008573116,0.0006969709,0.0002094308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000622586,0.000006418154,0.997417,0.000315964,0.0006072083,0.0006190858,0.000001184935,0.0002373939,0.000173111],"genre_scores_gemma":[0.81176,0.000002022842,0.1875453,0.0003029879,0.00003115107,0.0002223935,0.000003587957,0.00001879427,0.0001137023],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8111374,"threshold_uncertainty_score":0.8442227,"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."}}