{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007960053,0.0004985621,0.0006631818,0.0003023642,0.000254777,0.0001747944,0.0007794577,0.0005315833,0.0001051656],"category_scores_gemma":[0.001114234,0.000539003,0.0003103006,0.0004403742,0.00007131693,0.0005664751,0.001015643,0.000498109,7.154358e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002952911,"about_ca_system_score_gemma":0.001385587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002500403,"about_ca_topic_score_gemma":0.0002973097,"domain_scores_codex":[0.997942,0.0001016898,0.0003671411,0.0008624771,0.000136353,0.0005903046],"domain_scores_gemma":[0.9960464,0.001735912,0.0005204702,0.0008937993,0.0005141169,0.0002892641],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002243447,0.0009844755,0.009528873,0.02793655,0.001566118,0.000299864,0.007368139,0.08181037,0.002861022,0.8097255,0.03014487,0.0255308],"study_design_scores_gemma":[0.00195807,0.0001182523,0.00005643773,0.003062162,0.001431815,0.00001200461,0.00367627,0.09392773,0.001143349,0.8884119,0.004201769,0.00200025],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1692807,0.0002474917,0.8252416,0.00001082402,0.0006526852,0.0006777142,0.00003790189,0.0001410659,0.003709971],"genre_scores_gemma":[0.7036952,0.0003041867,0.292335,0.00002351454,0.0003208384,0.000002316073,0.00001580303,0.00006570184,0.003237408],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5344145,"threshold_uncertainty_score":0.9997061,"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."}}