{"id":"W1895872655","doi":"10.1002/9780470400531.eorms0714","title":"Reinforcement Learning Algorithms for<scp>MDPs</scp>","year":2011,"lang":"en","type":"other","venue":"Wiley Encyclopedia of Operations Research and Management Science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Learning classifier system; Machine learning; Focus (optics); Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002540329,0.0003235987,0.000339887,0.002015715,0.0008793671,0.0005279546,0.002648069,0.0001357796,0.00009932122],"category_scores_gemma":[0.0005934448,0.0003042056,0.000066081,0.001743475,0.00111858,0.0007664787,0.001980604,0.0004533461,0.0001047156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000993702,"about_ca_system_score_gemma":0.0002993525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002334987,"about_ca_topic_score_gemma":0.00003671518,"domain_scores_codex":[0.9955531,0.0000950814,0.0005052484,0.00104127,0.001758441,0.001046843],"domain_scores_gemma":[0.9978101,0.0001776482,0.0001618931,0.001094561,0.0004447536,0.000311059],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000004681202,0.0001705113,0.0001635586,0.0009077063,0.0001866517,0.00002212614,0.002217821,0.1042396,0.00007519977,0.4320779,0.4225878,0.03734634],"study_design_scores_gemma":[0.0003986011,0.0005881379,0.00007473315,0.0003381694,0.00001694172,0.000002349656,0.0002407744,0.2037748,0.00009271094,0.0002746751,0.7940202,0.0001779408],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.000005558186,0.0002578172,0.4970934,0.00004017435,0.0002781284,0.001198778,0.000002380077,0.0001070503,0.5010167],"genre_scores_gemma":[0.0004204162,0.02011356,0.1509841,0.00003756501,0.0001344873,0.0004083728,0.0000291441,0.00009830519,0.827774],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.4318033,"threshold_uncertainty_score":0.999941,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04620281988043152,"score_gpt":0.3262649527088484,"score_spread":0.2800621328284169,"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."}}