{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001402122,0.001115411,0.001096453,0.0003365554,0.000683277,0.001197547,0.001435806,0.001392852,0.002788364],"category_scores_gemma":[0.004071516,0.0007353195,0.001148969,0.0005258725,0.001309687,0.001540577,0.001733082,0.002559511,0.0003233403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007405536,"about_ca_system_score_gemma":0.001544673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003506643,"about_ca_topic_score_gemma":0.004015807,"domain_scores_codex":[0.999104,0.0002963775,0.00006889561,0.0002149946,0.0002140267,0.0001017964],"domain_scores_gemma":[0.9976673,0.001796606,0.0001889162,0.0001821065,0.00009379404,0.00007127925],"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":[0.00004284499,0.00005438978,0.0003391564,0.000169183,0.00004347706,0.00009119586,0.00007743819,0.9401262,0.001449681,0.02972532,0.0005001748,0.02738087],"study_design_scores_gemma":[0.00002283488,0.00002364715,0.00005424881,0.00001087339,0.000008636458,0.00002022393,0.00001395915,0.9738821,0.0008993567,0.02389197,0.001164885,0.00000718535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005089976,0.00008372937,0.9935992,0.00009713573,0.00001726445,0.00004536572,0.0000374978,0.0001974258,0.0008323282],"genre_scores_gemma":[0.2496398,0.0003214073,0.747938,0.00008365346,0.00004572331,0.0003099312,0.0001899369,0.00006881441,0.001402748],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003506643,"threshold_uncertainty_score":0.009328008,"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."}}