{"id":"W2122372591","doi":"","title":"Sketch-Based Linear Value Function Approximation","year":2012,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Hash function; Computer science; Estimator; Reinforcement learning; Universal hashing; Function approximation; Dynamic perfect hashing; Function (biology); Bellman equation; Hash table; Artificial intelligence; Algorithm; Mathematics; Mathematical optimization; Statistics; Double hashing; 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":[0.00200748,0.0009589338,0.001995664,0.0008045473,0.0003217821,0.001336015,0.002118814,0.001580765,0.004511326],"category_scores_gemma":[0.01225481,0.0005944119,0.0008097701,0.00118119,0.001031529,0.002443282,0.001930267,0.002244245,0.001225044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001262055,"about_ca_system_score_gemma":0.001149947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003320387,"about_ca_topic_score_gemma":0.00267392,"domain_scores_codex":[0.9988191,0.0004167172,0.00008362668,0.0002153268,0.0003397511,0.0001256082],"domain_scores_gemma":[0.9954163,0.003295138,0.0002330767,0.0004726076,0.000468632,0.0001143481],"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":[0.0001104819,0.00004668709,0.0008186057,0.0001232481,0.00003375923,0.00005612146,0.00007010454,0.8756562,0.0007994117,0.02260986,0.001841225,0.0978343],"study_design_scores_gemma":[0.000007582773,0.00001669333,0.00003147378,0.000005709521,0.000002167046,0.00000945649,0.000005184121,0.9918399,0.0001726915,0.007704261,0.0002017778,0.000002987303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01009844,0.0004935191,0.9871587,0.0001563446,0.00003075517,0.00005287165,0.0001045297,0.0005371105,0.00136773],"genre_scores_gemma":[0.6505452,0.0006539818,0.3429028,0.0002081762,0.0000853762,0.0004271832,0.0005895201,0.0001443244,0.004443439],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004511326,"threshold_uncertainty_score":0.0150919,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02141704514927115,"score_gpt":0.2476954964563511,"score_spread":0.2262784513070799,"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."}}