{"id":"W2139757085","doi":"10.48550/arxiv.1205.2643","title":"New inference strategies for solving Markov Decision Processes using reversible jump MCMC","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Markov chain Monte Carlo; Parameterized complexity; Computer science; Inference; Markov decision process; Reversible-jump Markov chain Monte Carlo; Markov chain; Jump; Sample (material); Order (exchange); Mathematical optimization; Markov process; Artificial intelligence; Machine learning; Algorithm; Mathematics; Bayesian probability; Statistics; Economics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.005141257,0.001236447,0.001477116,0.001378641,0.0007769843,0.001577086,0.003481761,0.001887964,0.004992179],"category_scores_gemma":[0.02037975,0.001134755,0.00145461,0.001136023,0.001991555,0.003044291,0.002359384,0.004334925,0.0007431754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001590069,"about_ca_system_score_gemma":0.0022334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004742352,"about_ca_topic_score_gemma":0.005996801,"domain_scores_codex":[0.9977192,0.001082602,0.0001275204,0.0004035298,0.000563762,0.0001033155],"domain_scores_gemma":[0.9900818,0.008416127,0.0004483514,0.0004562335,0.0004239392,0.0001734819],"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":[0.00004722506,0.00009232236,0.0005687313,0.0001834283,0.0001143434,0.0001185533,0.0001621261,0.6470878,0.001158982,0.2904128,0.001263304,0.05879043],"study_design_scores_gemma":[0.00001664888,0.000008513104,0.00003996115,0.00001473541,0.000009524955,0.00001235537,0.000005673666,0.9397668,0.000318934,0.058926,0.0008698315,0.00001113436],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008258271,0.0000896108,0.998408,0.00009624183,0.00001544848,0.00001957264,0.00001961824,0.00008126107,0.0004444278],"genre_scores_gemma":[0.1001578,0.0005541308,0.895918,0.000228461,0.0001438855,0.0003779618,0.000201039,0.0002594227,0.002159396],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005141257,"threshold_uncertainty_score":0.02718991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2767804058753422,"score_gpt":0.3130153136495329,"score_spread":0.03623490777419075,"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."}}