{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00190299,0.0008924506,0.001349678,0.0003692324,0.0003362269,0.001203269,0.001278156,0.001518259,0.003246419],"category_scores_gemma":[0.007979701,0.0004279292,0.0004833061,0.0003768031,0.001663432,0.001430638,0.001351804,0.001437764,0.0006724038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001080038,"about_ca_system_score_gemma":0.001780607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001994019,"about_ca_topic_score_gemma":0.001146782,"domain_scores_codex":[0.9987444,0.0005407333,0.00005282442,0.0002464064,0.0003060497,0.000109539],"domain_scores_gemma":[0.9970472,0.001862678,0.0002637508,0.0002751006,0.000442888,0.0001083672],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001006235,0.0000549424,0.0003513941,0.0001002468,0.00004240359,0.00005687468,0.00006817812,0.8846641,0.001187747,0.0785394,0.001001103,0.03383295],"study_design_scores_gemma":[0.000009769747,0.00002004354,0.00001784286,0.000005249155,0.000002668041,0.000009823469,0.000003211153,0.9895075,0.0003020564,0.009545557,0.0005728809,0.000003461987],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005806307,0.0001746568,0.9914238,0.000144066,0.00004951129,0.0000375534,0.00002070078,0.0001271745,0.00221619],"genre_scores_gemma":[0.6361047,0.0003598688,0.3534197,0.000308216,0.0001046043,0.0003865099,0.0001440059,0.0001506075,0.00902177],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003246419,"threshold_uncertainty_score":0.01086038,"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."}}