{"id":"W2342302999","doi":"","title":"Policy Optimization by Marginal-MAP Probabilistic Inference in Generative Models (Extended Abstract)","year":2014,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Partially observable Markov decision process; Computer science; Inference; Generative model; Probabilistic logic; Bounded function; Mathematical optimization; Representation (politics); Machine learning; Generative grammar; Bayesian inference; Artificial intelligence; Task (project management); Bayesian probability; Mathematics; Markov model; Markov chain","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":[0.0002937651,0.0001376888,0.0001429129,0.0001330537,0.00007118387,0.0001682058,0.0004472013,0.00005355584,0.00003457029],"category_scores_gemma":[0.0002170766,0.0001167312,0.00002437584,0.0003261819,0.000030011,0.0004742373,0.000110868,0.0001792804,0.00002798077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005314018,"about_ca_system_score_gemma":0.00009198584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000452605,"about_ca_topic_score_gemma":0.00002763455,"domain_scores_codex":[0.998881,0.00009719327,0.0002106756,0.0003660996,0.0001913458,0.0002536234],"domain_scores_gemma":[0.9993103,0.0001486593,0.00007263335,0.0003172253,0.00006923093,0.00008198164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000118286,0.00004748274,0.00003512801,0.000007651749,0.000001768249,7.771723e-7,0.0002183577,0.8349024,0.00003408208,0.1473915,0.0001869364,0.01717271],"study_design_scores_gemma":[0.0002154248,0.0000494211,0.0002381898,0.00001187618,8.346677e-7,0.000001032868,0.000004331692,0.9679999,0.00006798602,0.03107324,0.0001891273,0.0001486492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007578409,0.00001258239,0.9859411,0.002605961,0.00006573826,0.0001223053,0.00000123065,0.0001397689,0.01035348],"genre_scores_gemma":[0.7746293,0.000006289766,0.223272,0.0004217097,0.00007179972,0.0000214283,0.00001135802,0.000007470677,0.001558686],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7738715,"threshold_uncertainty_score":0.4760159,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01169152630604252,"score_gpt":0.265539861251298,"score_spread":0.2538483349452554,"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."}}