{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002296634,0.0001661273,0.0001887871,0.0001250593,0.0002856594,0.0001535472,0.0005251482,0.00002691538,0.00003444867],"category_scores_gemma":[0.00009155973,0.0001254517,0.00005244479,0.00056914,0.00002410127,0.001195791,0.00007881909,0.0002817404,0.0001381339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005368153,"about_ca_system_score_gemma":0.00004645443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001230737,"about_ca_topic_score_gemma":3.962141e-7,"domain_scores_codex":[0.9985718,0.0000758605,0.0002798935,0.0003111714,0.0004449215,0.0003163172],"domain_scores_gemma":[0.9989289,0.00008176845,0.0001801622,0.0006100362,0.00008497432,0.0001141827],"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":[0.000006364563,0.00001147427,0.0005675374,0.00001469468,0.00001154123,0.00001719699,0.0006377419,0.9761029,0.0001750628,0.007344254,0.0002423362,0.01486888],"study_design_scores_gemma":[0.0007592198,0.0009059412,0.007335083,0.0007592884,0.00002259711,0.00003820064,0.0001365097,0.9390879,0.002081612,0.0001124582,0.04828841,0.0004728095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00275974,0.000116282,0.9773687,0.001390868,0.0001340281,0.0002085096,5.238274e-8,0.0004114674,0.01761041],"genre_scores_gemma":[0.9655827,0.0004488093,0.03091472,0.0004265178,0.00008770639,0.000009689689,0.00001030481,0.00001415317,0.002505364],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.962823,"threshold_uncertainty_score":0.5115771,"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."}}