{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003780708,0.0008740266,0.001424952,0.0004980514,0.0003932761,0.001000498,0.001306849,0.001363577,0.001227991],"category_scores_gemma":[0.01516536,0.0005250463,0.0006662961,0.0004851047,0.001955744,0.001625393,0.001697021,0.001960756,0.0002736544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001465375,"about_ca_system_score_gemma":0.001937726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002661875,"about_ca_topic_score_gemma":0.001844202,"domain_scores_codex":[0.9984531,0.0008075041,0.00006056154,0.000203841,0.0003404117,0.0001345354],"domain_scores_gemma":[0.9917634,0.006250172,0.0006183216,0.0005418038,0.0006141468,0.0002121487],"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":[0.00007152772,0.00003535136,0.0003247665,0.00004125849,0.00002638009,0.00002635567,0.00003358021,0.9552456,0.00059812,0.0297938,0.0002472105,0.01355615],"study_design_scores_gemma":[0.00000356865,0.00001126213,0.00001280441,0.000001977864,9.834043e-7,0.000003096844,0.000001161033,0.9952909,0.0001327027,0.004475839,0.00006408222,0.000001613828],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01164427,0.0001213474,0.9873191,0.0001433026,0.00001811694,0.00001940904,0.00001157688,0.0001064008,0.0006166766],"genre_scores_gemma":[0.6549669,0.0001940436,0.3415856,0.0002195357,0.00005320558,0.00025381,0.00009956912,0.0001107453,0.002516699],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003780708,"threshold_uncertainty_score":0.01999456,"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."}}