{"id":"W1565394148","doi":"","title":"Solving POMDPs with continuous or large discrete observation spaces","year":2005,"lang":"en","type":"article","venue":"Discovery Research Portal (University of Dundee)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Toronto","funders":"","keywords":"Discretization; Markov decision process; Partially observable Markov decision process; Partition (number theory); Computer science; A priori and a posteriori; Observable; Task (project management); Domain (mathematical analysis); Mathematical optimization; Space (punctuation); Markov chain; Markov process; Theoretical computer science; Mathematics; Markov model; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008314434,0.0001409119,0.0002268994,0.0002435747,0.0004205968,0.0002594009,0.001109973,0.00007368274,0.000138812],"category_scores_gemma":[0.00006396885,0.0001269794,0.00007613484,0.0006483931,0.0002005194,0.003951567,0.0006359052,0.0003546178,0.00004466796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006539403,"about_ca_system_score_gemma":0.0003140507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002670277,"about_ca_topic_score_gemma":0.0008435079,"domain_scores_codex":[0.9975943,0.0001389547,0.0001538736,0.0003972494,0.00112405,0.0005915954],"domain_scores_gemma":[0.9986748,0.0001887231,0.0001733403,0.0005644602,0.0002626222,0.0001360803],"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":[0.001683598,0.001413916,0.2242722,0.000661005,0.001184051,0.002562731,0.04072569,0.1465106,0.003538767,0.537892,0.01825494,0.02130049],"study_design_scores_gemma":[0.005905414,0.003662081,0.1412405,0.0006791934,0.00008380294,0.00008858107,0.04448136,0.7508317,0.0009888115,0.0006765385,0.04987818,0.001483828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2696832,0.00005066704,0.7108397,0.001316432,0.00005293007,0.0003394888,0.000007927732,0.000132377,0.01757725],"genre_scores_gemma":[0.9590443,0.00008811311,0.02654484,0.00003296493,0.00004039532,4.453876e-7,0.00002015872,0.00001161506,0.01421714],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6893611,"threshold_uncertainty_score":0.5178071,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04698524795901635,"score_gpt":0.2927681737800475,"score_spread":0.2457829258210312,"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."}}