{"id":"W2101984404","doi":"","title":"VDCBPI: an Approximate Scalable Algorithm for Large POMDPs","year":2004,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Scalability; Markov decision process; Curse of dimensionality; Computer science; Bounded function; Markov process; Mathematical optimization; Observable; Algorithm; Theoretical computer science; Mathematics; Artificial intelligence","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":[0.0003593032,0.0001379346,0.0001361505,0.00007337848,0.0001990851,0.0002690145,0.0008424533,0.0000652018,0.00002752718],"category_scores_gemma":[0.00001916748,0.0001226601,0.00005933441,0.0002248702,0.00001294208,0.0008138879,0.0002010183,0.00009237252,0.0001219463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000684616,"about_ca_system_score_gemma":0.00007714945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001758674,"about_ca_topic_score_gemma":0.00000243705,"domain_scores_codex":[0.998662,0.0000167181,0.0002054665,0.0003578037,0.0002525749,0.0005054465],"domain_scores_gemma":[0.9990644,0.00003039167,0.00006474926,0.0006165988,0.00009263254,0.0001312183],"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":[0.000002315784,0.0002346402,0.00007276627,0.00002946709,0.00003008082,0.000007448249,0.0007300497,0.2024935,0.0001861681,0.771414,0.0008072557,0.02399227],"study_design_scores_gemma":[0.0009380776,0.0002258089,0.00004475978,0.000007123531,0.000004447545,0.00000727455,0.00002677084,0.9807162,0.002380204,0.004385432,0.01107148,0.0001924669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000182423,0.00001150776,0.9914038,0.0003318774,0.0002808889,0.000323354,0.000001793228,0.0006567004,0.00680764],"genre_scores_gemma":[0.0147528,0.00000408594,0.9812412,0.0006494197,0.00008023324,0.00003137075,0.00001162572,0.00001664916,0.003212566],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7782226,"threshold_uncertainty_score":0.5001933,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01861896870123979,"score_gpt":0.2662121577549219,"score_spread":0.2475931890536821,"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."}}