{"id":"W1506128430","doi":"","title":"Compact, convex upper bound iteration for approximate POMDP planning","year":2006,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Alberta","funders":"","keywords":"Partially observable Markov decision process; Mathematical optimization; Markov decision process; Upper and lower bounds; Bellman equation; Bounded function; Computer science; Piecewise; Heuristic; Linear programming; Convex optimization; Semidefinite programming; Time horizon; Mathematics; Function (biology); Regular polygon; Markov process","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":[0.002646857,0.001216844,0.001596718,0.000613738,0.0005096804,0.001506891,0.001357778,0.001112957,0.002183552],"category_scores_gemma":[0.0100954,0.0008115987,0.0008914953,0.000757198,0.002058212,0.001926214,0.001921236,0.002749345,0.0005014074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001654911,"about_ca_system_score_gemma":0.001695146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003107834,"about_ca_topic_score_gemma":0.002795999,"domain_scores_codex":[0.9982376,0.0006035686,0.00008370588,0.0002524494,0.0006887818,0.0001339443],"domain_scores_gemma":[0.9955525,0.003243864,0.0003060142,0.000454483,0.0003122392,0.0001308362],"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":[0.00006375741,0.00003040685,0.0001578273,0.00005001061,0.00001275694,0.00002963497,0.00006369579,0.9447373,0.0006321865,0.03686451,0.0005040354,0.01685391],"study_design_scores_gemma":[0.00000360687,0.000009284661,0.000008347438,0.00000373887,0.000001067039,0.0000036933,0.00000311134,0.9913771,0.000195494,0.008207978,0.0001847433,0.000001772761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003980388,0.00008418248,0.9940979,0.00007141559,0.00001012633,0.0000234887,0.00002288744,0.0002213408,0.001488245],"genre_scores_gemma":[0.4678614,0.0002927773,0.5277713,0.0001185402,0.00004159522,0.0004395311,0.0002425695,0.0002501206,0.002982145],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003107834,"threshold_uncertainty_score":0.01399809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01338592560030774,"score_gpt":0.2710485755621948,"score_spread":0.257662649961887,"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."}}