{"id":"W2395526823","doi":"","title":"An empirical analysis of reinforcement learning using design of experiments","year":2013,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Convergence (economics); Computer science; Reinforcement learning; Artificial neural network; Subspace topology; Design of experiments; Logistic regression; Regression; Artificial intelligence; Machine learning; Mathematical optimization; Algorithm; Statistics; 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":[0.0003380461,0.0001234323,0.0003169288,0.0004266145,0.00006004223,0.00006530138,0.0006618947,0.00005341459,0.000396187],"category_scores_gemma":[0.00004657131,0.0001080741,0.0001038674,0.001099562,0.00004930901,0.0006301522,0.0001839995,0.0000903087,0.00001231373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004633691,"about_ca_system_score_gemma":0.00005110035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002064536,"about_ca_topic_score_gemma":2.150279e-7,"domain_scores_codex":[0.9983603,0.0001496903,0.000532706,0.0002409562,0.0004833562,0.0002330231],"domain_scores_gemma":[0.9987155,0.00009779438,0.0003195656,0.0005814419,0.0001952117,0.00009047021],"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":[0.00000227912,0.00002796811,0.01109388,0.000004732099,0.0002231822,3.425982e-7,0.0009289053,0.9619579,0.02482932,0.0005648407,0.00002090249,0.0003457181],"study_design_scores_gemma":[0.0001373279,0.0002801396,0.00233435,0.000007365922,0.00007901366,3.559389e-7,0.0001487402,0.9751415,0.02173716,0.00001314523,0.00001039778,0.0001104651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06471152,0.000008031025,0.9341366,0.00001304353,0.00003943599,0.0001677723,3.091745e-8,0.00005264014,0.0008709454],"genre_scores_gemma":[0.74068,0.000002082224,0.25903,0.00004382566,0.000004724482,0.000004095094,0.000002020506,0.000005094256,0.000228158],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6759685,"threshold_uncertainty_score":0.4407132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08287195625593569,"score_gpt":0.3503770929916817,"score_spread":0.267505136735746,"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."}}