{"id":"W2107952055","doi":"10.5555/2343896.2343940","title":"Analysis of methods for solving MDPs","year":2012,"lang":"en","type":"article","venue":"Adaptive Agents and Multi-Agents Systems","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Convergence (economics); Mathematical proof; Simple (philosophy); Computer science; Mathematical optimization; Value (mathematics); Function (biology); Bellman equation; Power iteration; Markov decision process; Applied mathematics; Mathematics; Algorithm; Iterative method; Markov process; 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":[0.002320733,0.0001737155,0.0004366989,0.0003138215,0.000143119,0.00006304894,0.0004384435,0.0000882672,0.000005405712],"category_scores_gemma":[0.0001930258,0.0001505456,0.0001607116,0.0006275414,0.00004946816,0.0006633002,0.000187292,0.00006462944,0.000004020873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005066496,"about_ca_system_score_gemma":0.00001577665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001745358,"about_ca_topic_score_gemma":0.000002106271,"domain_scores_codex":[0.9982892,0.00033944,0.00047985,0.0003469801,0.0001717828,0.0003727408],"domain_scores_gemma":[0.9985173,0.0002360935,0.0003913237,0.0005073785,0.0001889841,0.0001589046],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001245694,0.001721222,0.1331937,0.0007539678,0.01056352,0.000002499504,0.03254069,0.004266448,0.02091027,0.2964965,0.001090682,0.498336],"study_design_scores_gemma":[0.0003638495,0.0000588995,0.07356718,0.00002615915,0.0003189656,0.000002055385,0.0003248005,0.9191619,0.001061217,0.00001655537,0.004916276,0.0001821136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01575179,0.001320029,0.9809777,0.000007062689,0.001075205,0.0005907039,0.00002064352,0.0000426321,0.0002142678],"genre_scores_gemma":[0.4701879,0.00003948016,0.5294597,0.00002795064,0.00003404672,0.00006580222,0.00000474426,0.000008320038,0.0001720671],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9148955,"threshold_uncertainty_score":0.613907,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1869371033501745,"score_gpt":0.4286122566916662,"score_spread":0.2416751533414916,"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."}}