{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00193592,0.0002681305,0.0002488774,0.0003927785,0.001826012,0.001537834,0.0006532875,0.00007795977,0.00005081133],"category_scores_gemma":[0.003144329,0.0002358419,0.00001832968,0.002424832,0.002000708,0.0009062255,0.0003574946,0.0006755674,0.00001690751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001911313,"about_ca_system_score_gemma":0.0009823946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006124946,"about_ca_topic_score_gemma":0.000001518596,"domain_scores_codex":[0.9964737,0.0001989344,0.0004132342,0.001034265,0.001111839,0.0007680326],"domain_scores_gemma":[0.9969248,0.001907257,0.0002061889,0.0003924386,0.0003125946,0.000256788],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006368088,0.00001962711,0.009864411,0.0001081234,0.00000934935,0.000006008918,0.0003564261,0.5963333,0.0001611817,0.3364645,0.00002889406,0.05658457],"study_design_scores_gemma":[0.0005251179,0.0007725439,0.04181777,0.0003134123,0.0000420312,0.000003035691,0.0001367872,0.9528265,0.0001246369,0.002414254,0.000758955,0.0002649639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001329785,0.00007229621,0.9928828,0.0004591089,0.0004405079,0.0003231865,0.000003959608,0.0001215208,0.004366872],"genre_scores_gemma":[0.7320212,0.000002499283,0.2673717,0.0002880975,0.00002031047,0.00001003249,0.000006760847,0.000006569734,0.0002728506],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7306914,"threshold_uncertainty_score":0.9994987,"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."}}