{"id":"W2127186087","doi":"10.7282/t3zw1qcr","title":"Exploring compact reinforcement-learning representations with linear regression","year":2009,"lang":"en","type":"article","venue":"View","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Linear regression; Artificial intelligence; Function (biology); Regression; Object (grammar); Machine learning; Mathematical optimization; Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001447504,0.0008362883,0.001411866,0.0004416794,0.0002984253,0.0009757004,0.001399853,0.001055175,0.002427524],"category_scores_gemma":[0.006962114,0.0006412147,0.0005830981,0.0006103072,0.001198323,0.002630588,0.001817192,0.001819271,0.0006401791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008265143,"about_ca_system_score_gemma":0.000870304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002204519,"about_ca_topic_score_gemma":0.001514357,"domain_scores_codex":[0.9993482,0.0002844075,0.00003136621,0.0001445435,0.0001264747,0.00006495079],"domain_scores_gemma":[0.9979057,0.001574234,0.0001601806,0.0001818622,0.0001331396,0.00004477707],"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":[0.00008327608,0.00006568302,0.0003645152,0.00007777158,0.00002964481,0.00005192021,0.0001011784,0.8828509,0.001206021,0.04445457,0.0009837061,0.06973081],"study_design_scores_gemma":[0.000008919291,0.00001124469,0.00001203836,0.000003358555,0.000001948988,0.000006223932,0.000005151806,0.9869016,0.0002019374,0.01266649,0.0001787622,0.000002369122],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008624167,0.0001015301,0.9901445,0.00009570039,0.000008257055,0.00001459753,0.0000143917,0.0004157031,0.0005810938],"genre_scores_gemma":[0.5881768,0.0002578664,0.4078155,0.0002001922,0.00003807258,0.000245586,0.0001922153,0.0002675882,0.00280603],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002427524,"threshold_uncertainty_score":0.008120835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1029354142745587,"score_gpt":0.3145732768541596,"score_spread":0.2116378625796009,"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."}}