{"id":"W1794176462","doi":"10.48550/arxiv.1301.2304","title":"Vector-space Analysis of Belief-state Approximation for POMDPs","year":2013,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Approximation algorithm; State space; Approximation error; Mathematical optimization; Space (punctuation); State (computer science); Quality (philosophy); Value (mathematics); Artificial intelligence; Algorithm; Mathematics; Machine learning","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":[0.00418966,0.001080634,0.001470878,0.001678401,0.0006967062,0.002252125,0.002301187,0.001448937,0.004115224],"category_scores_gemma":[0.01671211,0.0008055204,0.00153267,0.001686343,0.002039177,0.003998848,0.002326119,0.003169094,0.0005716019],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002492701,"about_ca_system_score_gemma":0.002015557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007370649,"about_ca_topic_score_gemma":0.004300076,"domain_scores_codex":[0.9973047,0.001162772,0.0001404736,0.0003298685,0.0008698598,0.0001922987],"domain_scores_gemma":[0.9909711,0.007092045,0.0004732972,0.0004916633,0.0008064932,0.0001654632],"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":[0.00005052351,0.0000295092,0.0004511231,0.0000921696,0.00004141928,0.00002375363,0.00008413188,0.7994002,0.0004359118,0.1784317,0.0006880962,0.02027139],"study_design_scores_gemma":[0.000003965348,0.000006875915,0.00003043692,0.000007310723,0.000003435072,0.000002991047,0.000005469691,0.9538334,0.0001395183,0.04568771,0.0002741189,0.000004797609],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002334722,0.0001047944,0.9966487,0.0001049026,0.00001271168,0.00001311475,0.0000307446,0.00007624186,0.0006739724],"genre_scores_gemma":[0.4665622,0.0007845096,0.5285368,0.0001887977,0.0001230834,0.000311615,0.0004314984,0.0002116279,0.002849972],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007370649,"threshold_uncertainty_score":0.02215725,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05598216329112023,"score_gpt":0.1835560925630462,"score_spread":0.127573929271926,"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."}}