{"id":"W2406623448","doi":"10.5555/2615731.2616087","title":"Policy optimization by marginal-map probabilistic inference in generative models","year":2014,"lang":"en","type":"article","venue":"Adaptive Agents and Multi-Agents Systems","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Partially observable Markov decision process; Inference; Computer science; Mathematical optimization; Generative model; Bounded function; Benchmark (surveying); Probabilistic logic; Machine learning; Artificial intelligence; Algorithm; Mathematics; Generative grammar; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002307604,0.001027224,0.00154974,0.00072295,0.0005871528,0.001444503,0.00213118,0.001488845,0.002456649],"category_scores_gemma":[0.008791993,0.0009983853,0.001265553,0.0008673642,0.002164701,0.001734786,0.00224847,0.002554654,0.0003007935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001961825,"about_ca_system_score_gemma":0.002474535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01225253,"about_ca_topic_score_gemma":0.01078256,"domain_scores_codex":[0.9990145,0.0003943314,0.00003989859,0.0002065785,0.0002346467,0.0001100444],"domain_scores_gemma":[0.9966587,0.002694343,0.00018808,0.0001939857,0.0001713958,0.00009347894],"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":[0.00002232751,0.0000129799,0.000193637,0.00003077038,0.00001691233,0.00002006206,0.0000339364,0.9727623,0.0002128758,0.01948529,0.0002251341,0.006983835],"study_design_scores_gemma":[0.000003645295,0.000003937781,0.00001971305,0.000002541651,0.000002473116,0.000003633065,0.00000361859,0.9902439,0.0001117586,0.009500965,0.000101657,0.000002336861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004550365,0.00008784854,0.9943606,0.00011042,0.000009717322,0.00001698866,0.00003099137,0.0001736226,0.0006594795],"genre_scores_gemma":[0.6322411,0.0003149812,0.3644221,0.0001941363,0.00006045734,0.000231506,0.0002357428,0.0002197969,0.002080194],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01225253,"threshold_uncertainty_score":0.02436244,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03596804359116691,"score_gpt":0.2878306369712302,"score_spread":0.2518625933800633,"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."}}