{"id":"W3167624337","doi":"","title":"Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient","year":2021,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Minimax; Estimator; Reinforcement learning; Lasso (programming language); Upper and lower bounds; Covariance; Divergence (linguistics); Computer science; Sample size determination; Feature selection; Mathematical optimization; Dimension (graph theory); Mathematics; Function (biology); Model selection; Algorithm; Artificial intelligence; Statistics","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004387585,0.0003343341,0.0002616923,0.0002681706,0.0004466509,0.0007172424,0.0008857436,0.0001332196,0.0009744776],"category_scores_gemma":[0.001135084,0.0003391957,0.000140639,0.0004849642,0.00004844215,0.000303351,0.0004750955,0.001496152,0.0002152796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002599018,"about_ca_system_score_gemma":0.0002058634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001043456,"about_ca_topic_score_gemma":0.00001265123,"domain_scores_codex":[0.9970066,0.0002472409,0.0004025318,0.0007169991,0.001156339,0.0004702859],"domain_scores_gemma":[0.9982356,0.0002822117,0.0003378621,0.0003489208,0.0006555527,0.0001398482],"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":[0.00002323396,0.00003504844,0.007213074,0.00001118329,0.00005333046,0.00003468237,0.0005944411,0.9012622,0.001639401,0.08434716,0.0001337439,0.004652457],"study_design_scores_gemma":[0.000519483,0.000195574,0.001542471,0.0001122118,0.00001042013,0.00005000647,0.0001905675,0.9698751,0.001623267,0.0001736002,0.02536752,0.0003397933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006057122,0.00003912461,0.9648504,0.005956835,0.0008455479,0.0001465906,0.000001954702,0.0004199643,0.02168242],"genre_scores_gemma":[0.9597772,0.00007009845,0.01968274,0.0005678363,0.0001843572,0.00002026262,0.0002098407,0.00003025486,0.01945743],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.95372,"threshold_uncertainty_score":0.9999388,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03003771541059881,"score_gpt":0.2933460117824498,"score_spread":0.263308296371851,"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."}}