{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0857745,0.001145249,0.001270743,0.001066652,0.0004487301,0.001495502,0.001505503,0.001437586,0.001289684],"category_scores_gemma":[0.2300372,0.0006223129,0.001197285,0.0006200632,0.002421138,0.001469367,0.0009734436,0.001942233,0.00014589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002260792,"about_ca_system_score_gemma":0.00127706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006320043,"about_ca_topic_score_gemma":0.0003924114,"domain_scores_codex":[0.9294894,0.05980341,0.0023052,0.003099642,0.004291806,0.001010556],"domain_scores_gemma":[0.3903629,0.5649916,0.01835345,0.01813478,0.007224732,0.0009324943],"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":[0.03065,0.01463484,0.09613352,0.00306754,0.005058466,0.000541796,0.002876525,0.5165874,0.02615046,0.1133876,0.003992373,0.1869195],"study_design_scores_gemma":[0.002689396,0.02965135,0.01867199,0.0002236679,0.0006807835,0.0001821902,0.0003294226,0.9035986,0.01592159,0.0248931,0.00301341,0.0001445362],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6217746,0.000392724,0.3716557,0.0003110036,0.0001982152,0.002369466,0.0002907922,0.0002686674,0.002738881],"genre_scores_gemma":[0.932436,0.00007225708,0.06372894,0.0001165489,0.0000343633,0.002965979,0.000140927,0.00003865287,0.0004662926],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0857745,"threshold_uncertainty_score":0.4536244,"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."}}