{"id":"W1503109067","doi":"","title":"Point-Based Value Iteration for Constrained POMDPs","year":2012,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Markov decision process; Mathematical optimization; Bellman equation; Computer science; Dynamic programming; Minimax; Linear programming; Value (mathematics); Scalability; Function (biology); Point (geometry); Markov process; Mathematics","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":[0.0003200189,0.00007989119,0.00007255595,0.00006143504,0.00008110327,0.0001390468,0.0002639186,0.00003812855,0.00003880953],"category_scores_gemma":[0.00008115696,0.00007037247,0.00004781724,0.0001065748,0.00001592942,0.0006927361,0.00003896514,0.00004431991,0.00008624126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003096545,"about_ca_system_score_gemma":0.00004676911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002589385,"about_ca_topic_score_gemma":1.743106e-7,"domain_scores_codex":[0.9992961,0.00002026421,0.0001525836,0.0001216762,0.0001469148,0.0002624812],"domain_scores_gemma":[0.999401,0.000144801,0.00005860071,0.0002681887,0.00006518309,0.00006216416],"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":[0.000002784129,0.00004053575,0.0006082109,0.00001659909,0.000008489084,2.113922e-7,0.0001899906,0.09323391,0.0006111129,0.9024014,0.001886614,0.001000155],"study_design_scores_gemma":[0.0003991692,0.00008411358,0.0001943241,0.000005044091,0.000004286941,0.000002308087,0.000007559152,0.9859285,0.003383895,0.0002657837,0.009615591,0.00010938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004403031,0.000007123725,0.9868466,0.0009415396,0.0004218336,0.0002390062,3.461804e-7,0.0002817762,0.01082148],"genre_scores_gemma":[0.5457948,1.608899e-7,0.4521152,0.001317063,0.00008785736,0.00001427291,0.000006245439,0.000004888925,0.000659398],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9021356,"threshold_uncertainty_score":0.2869706,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02092790281422207,"score_gpt":0.2662145478222802,"score_spread":0.2452866450080581,"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."}}