{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003534133,0.00008039075,0.0000631605,0.00007110959,0.00007886826,0.00006184925,0.000255051,0.00004714622,0.00006944839],"category_scores_gemma":[0.00004544439,0.00006978396,0.00003611722,0.0002272715,0.00001403431,0.0007489217,0.0000626839,0.00008616862,0.0005828433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000037118,"about_ca_system_score_gemma":0.00002550536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000062111,"about_ca_topic_score_gemma":1.32729e-7,"domain_scores_codex":[0.9991817,0.00004416882,0.0001455511,0.0001271164,0.0002641858,0.0002372754],"domain_scores_gemma":[0.9994084,0.00005104312,0.00006519293,0.0003551639,0.00004547541,0.00007475005],"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":[0.000003448303,0.00004009251,0.002832972,0.00001460996,0.000007565838,1.58082e-7,0.0001355618,0.8079687,0.0003228223,0.1809852,0.0008463667,0.006842533],"study_design_scores_gemma":[0.0001576462,0.00005155748,0.002610826,0.000004028433,0.000004366387,8.659815e-7,0.000006592004,0.9865744,0.002015205,0.0001472678,0.008332275,0.0000950292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001026765,0.00001231597,0.9823925,0.0003008601,0.0006285253,0.0001066343,4.653984e-8,0.0003308993,0.01520144],"genre_scores_gemma":[0.7009897,5.828298e-7,0.2966525,0.0007200141,0.0001478053,0.000007227467,0.000005511752,0.000006468613,0.001470166],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.699963,"threshold_uncertainty_score":0.7491465,"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."}}