{"id":"W2520501711","doi":"","title":"Regularized policy iteration with nonparametric function spaces","year":2016,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Markov decision process; Mathematical optimization; Reproducing kernel Hilbert space; Reinforcement learning; Mathematics; Regularization (linguistics); Function space; Nonparametric statistics; Bellman equation; Minimax; Function (biology); Computer science; Applied mathematics; Hilbert space; Markov process; Artificial intelligence; Discrete mathematics","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":[0.0005754485,0.0003282181,0.0002849691,0.001121002,0.0002683091,0.0006264055,0.0008785842,0.0002092238,0.00002072291],"category_scores_gemma":[0.0003762424,0.0002274491,0.0001009325,0.001981131,0.00009185708,0.001482217,0.0002605954,0.0002337797,0.00007078295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005845184,"about_ca_system_score_gemma":0.0003539122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001099506,"about_ca_topic_score_gemma":0.0001478115,"domain_scores_codex":[0.9975299,0.0001552216,0.0004024317,0.0005706333,0.0006350826,0.0007067557],"domain_scores_gemma":[0.9977006,0.000203691,0.000337238,0.001301889,0.0002055599,0.0002509851],"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":[0.0003123218,0.0001847178,0.03491678,0.0000446912,0.0001577664,0.00005999627,0.0003971184,0.1099032,0.04883586,0.6737007,0.002519546,0.1289673],"study_design_scores_gemma":[0.002854094,0.00168802,0.05995596,0.0002347037,0.00005827831,0.0002332978,0.00003177677,0.8899009,0.02414841,0.007276967,0.01240575,0.001211824],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01216852,0.00009289952,0.9746076,0.01037287,0.0001345012,0.0005308257,0.000002433996,0.001162718,0.0009276564],"genre_scores_gemma":[0.7332672,0.00005985542,0.2606237,0.001345773,0.0001653468,0.0001680306,0.000005675558,0.00004001693,0.00432435],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7799978,"threshold_uncertainty_score":0.9275103,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008502984474690533,"score_gpt":0.2192352149430466,"score_spread":0.2107322304683561,"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."}}