{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005835325,0.001166375,0.0008938765,0.001025976,0.0006505648,0.001789427,0.001936684,0.001321411,0.006042571],"category_scores_gemma":[0.02243604,0.0008546554,0.001669251,0.0008814869,0.002951293,0.00276007,0.00310745,0.002591587,0.0005352688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00185699,"about_ca_system_score_gemma":0.001984999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001905478,"about_ca_topic_score_gemma":0.001850298,"domain_scores_codex":[0.9958398,0.001698391,0.0002645348,0.0005136686,0.001409326,0.0002742813],"domain_scores_gemma":[0.9833655,0.01417364,0.0005304795,0.001013928,0.0007621142,0.0001543699],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009347699,0.00004999752,0.0005438384,0.0005695281,0.0001151365,0.00008493565,0.0002865934,0.28934,0.001561406,0.6318665,0.001383617,0.07410493],"study_design_scores_gemma":[0.00005162791,0.00003439436,0.0000708965,0.00008107406,0.0000215458,0.00003550013,0.0000262954,0.6306882,0.001565378,0.3622838,0.005129552,0.00001181056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00337856,0.0002709607,0.9933536,0.0001654043,0.00002437323,0.00007319724,0.00004051479,0.0001788505,0.00251461],"genre_scores_gemma":[0.2445945,0.0006273009,0.7490056,0.0001540325,0.00007874372,0.0007512002,0.0002089086,0.0002435816,0.004336073],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006042571,"threshold_uncertainty_score":0.03086054,"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."}}