{"id":"W1527719492","doi":"10.48550/arxiv.1301.3887","title":"Value-Directed Belief State Approximation for POMDPs","year":2013,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Distributed Sensor Networks and Detection Algorithms","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Partially observable Markov decision process; Markov decision process; Heuristic; Computer science; Bellman equation; Mathematical optimization; State (computer science); Projection (relational algebra); Divergence (linguistics); Approximation error; Markov process; Approximation algorithm; Observable; Expected utility hypothesis; Decision problem; Function (biology); Mathematics; Algorithm; Mathematical economics; Statistics","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":[0.004440919,0.001172819,0.001559679,0.0009325859,0.0006750273,0.001974472,0.002129889,0.001380102,0.002273703],"category_scores_gemma":[0.01920478,0.0007286626,0.001274917,0.001250366,0.001981302,0.002764755,0.002619389,0.003194783,0.0003616743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002749405,"about_ca_system_score_gemma":0.001675864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004416063,"about_ca_topic_score_gemma":0.003776115,"domain_scores_codex":[0.9974982,0.001084172,0.0001211787,0.0004234772,0.000675716,0.0001971849],"domain_scores_gemma":[0.9902549,0.007790695,0.0005384109,0.0005888744,0.0006031535,0.0002240222],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000888114,0.00003482621,0.0005646704,0.00009942782,0.00003683488,0.0000361539,0.0001331193,0.8846543,0.000427953,0.09086506,0.0005120959,0.02254676],"study_design_scores_gemma":[0.000007185567,0.00001253229,0.00002970608,0.00001122701,0.000005279184,0.000006999862,0.00001048905,0.9642264,0.0002254425,0.03516473,0.0002957682,0.000004153321],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003341785,0.00009811234,0.99559,0.00009426584,0.00001061327,0.00002324787,0.00002508809,0.00009669245,0.000720255],"genre_scores_gemma":[0.4560674,0.0004286721,0.5406806,0.0001391332,0.00004956308,0.0002626403,0.0002713592,0.0001159061,0.001984621],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004440919,"threshold_uncertainty_score":0.02348608,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03129508124226996,"score_gpt":0.1617893819799374,"score_spread":0.1304943007376675,"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."}}