{"id":"W7118628814","doi":"10.1214/25-sts1001","title":"Sample-Based Planning and Learning with Function Approximation","year":2025,"lang":"","type":"article","venue":"Statistical Science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Function approximation; Core (optical fiber); Focus (optics); Dimension (graph theory); Function (biology); Approximation algorithm; Optimism","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":[0.002408563,0.002051888,0.001257641,0.001058645,0.0003862145,0.002254158,0.001761117,0.001927247,0.01095742],"category_scores_gemma":[0.00658453,0.001046265,0.001519102,0.001735643,0.002233313,0.00382229,0.001988155,0.003588252,0.002871625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001511169,"about_ca_system_score_gemma":0.0009642252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001727018,"about_ca_topic_score_gemma":0.001484669,"domain_scores_codex":[0.9984748,0.0006130185,0.0001087083,0.0002960112,0.0004191072,0.00008837882],"domain_scores_gemma":[0.9982249,0.001407006,0.00007895041,0.0001364755,0.0001048689,0.00004790558],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007214645,0.00006205123,0.0002715059,0.0009272012,0.00008267877,0.0001178845,0.0001651389,0.08001696,0.00197843,0.7215514,0.01142681,0.1833279],"study_design_scores_gemma":[0.00002870947,0.0001042551,0.0002590294,0.0002345247,0.00003253559,0.0001539097,0.00002748691,0.1818812,0.001713922,0.7678395,0.0476783,0.00004663612],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005196238,0.00511744,0.9890637,0.0003635885,0.0001488273,0.00003528734,0.00009848711,0.0002947818,0.004358327],"genre_scores_gemma":[0.07074305,0.02219505,0.8921829,0.0007754823,0.00135528,0.0006933687,0.0007913291,0.0006291923,0.01063439],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01095742,"threshold_uncertainty_score":0.0366562,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01549883190499455,"score_gpt":0.2817929071851326,"score_spread":0.266294075280138,"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."}}