{"id":"W2963097726","doi":"10.1609/aaai.v33i01.33014384","title":"The Utility of Sparse Representations for Control in Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Sparse approximation; Computer science; Neural coding; Bootstrapping (finance); Artificial intelligence; Representation (politics); Machine learning; Artificial neural network; Locality; Mathematics","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":[0.00121029,0.0001483163,0.0002478248,0.00009228829,0.0001814878,0.0001422239,0.001715291,0.0000590479,0.00003913264],"category_scores_gemma":[0.001160285,0.0001006694,0.0001071671,0.0004649673,0.0002099581,0.0002881547,0.0002553444,0.0002913302,0.00002585904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003296167,"about_ca_system_score_gemma":0.0001011627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004670964,"about_ca_topic_score_gemma":0.000008056903,"domain_scores_codex":[0.9980797,0.00003054373,0.0007682811,0.0003293435,0.0004708603,0.0003212896],"domain_scores_gemma":[0.9977136,0.0005579638,0.0006543121,0.0003915503,0.0006429854,0.00003954447],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001420115,0.00004345335,0.004997279,0.00005840707,0.00001996546,6.240522e-8,0.001250829,0.1786175,0.009504087,0.7957736,0.00007729853,0.009515489],"study_design_scores_gemma":[0.00008312483,0.0002641686,0.0008704393,0.0001174412,0.000006968587,4.568967e-7,0.0006582504,0.9182219,0.06041602,0.0190627,0.0001967194,0.0001018295],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06049748,0.00001910288,0.9095155,0.00336381,0.0006481271,0.002220476,0.000001657154,0.00005955494,0.02367429],"genre_scores_gemma":[0.9978248,0.00002319853,0.001109905,0.00006512476,0.00001610386,0.00004986652,3.990725e-7,0.000007289918,0.0009033142],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9373273,"threshold_uncertainty_score":0.4105178,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06591031971543576,"score_gpt":0.3089931647799222,"score_spread":0.2430828450644865,"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."}}