{"id":"W2158738729","doi":"","title":"Regularized Policy Iteration","year":2008,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; University of Alberta","funders":"","keywords":"Reinforcement learning; Mathematical optimization; Regularization (linguistics); Reproducing kernel Hilbert space; Temporal difference learning; Computer science; Bellman equation; Markov decision process; Kernel (algebra); Residual; Hilbert space; Parametric statistics; Convergence (economics); Function approximation; Rate of convergence; Algorithm; Mathematics; Artificial intelligence; Markov process; Artificial neural network","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004707746,0.0003094737,0.0002998483,0.0006595723,0.0005060619,0.0003137203,0.001314647,0.0002315038,0.00001861109],"category_scores_gemma":[0.0003584282,0.0003197571,0.000161207,0.001150244,0.0001027783,0.001056909,0.0004395104,0.000400826,0.00009018645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000498026,"about_ca_system_score_gemma":0.0005043736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001971768,"about_ca_topic_score_gemma":0.00006714044,"domain_scores_codex":[0.9974926,0.0001566324,0.0005062401,0.0005044159,0.0005875275,0.0007525987],"domain_scores_gemma":[0.9977376,0.00009501584,0.0002518614,0.001471461,0.0001563304,0.0002877525],"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":[0.00004563012,0.0001717061,0.01674935,0.00003131398,0.00007035593,0.0002627503,0.001766233,0.3087007,0.02135608,0.6291784,0.008296905,0.01337061],"study_design_scores_gemma":[0.0005910139,0.0001541286,0.01993431,0.00002518357,0.000007102347,0.0004419751,0.000009519779,0.9604462,0.008672397,0.002380203,0.006897449,0.0004405379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01190158,0.0001304425,0.9768935,0.006540798,0.0001533279,0.0004497047,0.000002049966,0.001467012,0.002461625],"genre_scores_gemma":[0.5925515,0.000128722,0.3984527,0.003250908,0.0002097861,0.0001312214,0.00001464619,0.00003765041,0.005222841],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6517456,"threshold_uncertainty_score":0.9999254,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01361379034717296,"score_gpt":0.2341841148069613,"score_spread":0.2205703244597883,"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."}}