{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001521004,0.0007310212,0.001034584,0.0005719431,0.0005152264,0.0009725865,0.001336839,0.001064967,0.004281505],"category_scores_gemma":[0.0052621,0.0003455837,0.0004105322,0.0006756886,0.001208139,0.0009001499,0.001538832,0.001795173,0.0005147647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001425948,"about_ca_system_score_gemma":0.001298436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006266804,"about_ca_topic_score_gemma":0.00394158,"domain_scores_codex":[0.9994707,0.0002167663,0.000029511,0.00007538997,0.0001437155,0.0000640253],"domain_scores_gemma":[0.9976293,0.001648238,0.0001928597,0.0001155638,0.0003000531,0.0001139906],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003164847,0.0000303936,0.0001952438,0.00003848558,0.00001598673,0.00003168583,0.00002607161,0.9344907,0.000153432,0.03761403,0.001464259,0.025908],"study_design_scores_gemma":[0.00001179562,0.000007608022,0.00001563778,0.000004309196,0.000001381065,0.000004489816,0.000002185044,0.9853324,0.00006465807,0.01422846,0.0003253394,0.000001698382],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01625904,0.000486182,0.9750117,0.0005794013,0.00005840645,0.00008489,0.00005722141,0.0003304832,0.007132602],"genre_scores_gemma":[0.7277766,0.0005772987,0.2638056,0.0002344204,0.0001156715,0.0004355911,0.0001884138,0.0001611512,0.006705333],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006266804,"threshold_uncertainty_score":0.014323,"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."}}