{"id":"W2144794447","doi":"","title":"Bayes-Adaptive POMDPs","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":112,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; McGill University","funders":"","keywords":"Partially observable Markov decision process; Reinforcement learning; Computer science; Markov decision process; Bellman equation; Artificial intelligence; Bayesian probability; Machine learning; Bayes' theorem; Markov process; Markov chain; Mathematical optimization; Markov model; Mathematics","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":[0.0004021169,0.00007206541,0.0000627179,0.00007013811,0.00006101012,0.00006755251,0.0005549037,0.00003370327,0.00005390037],"category_scores_gemma":[0.00002369234,0.00006167231,0.00003183405,0.0002348636,0.00001492526,0.0002768964,0.0001247725,0.00009398271,0.0004751258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003904704,"about_ca_system_score_gemma":0.00002412362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001061543,"about_ca_topic_score_gemma":0.000002373072,"domain_scores_codex":[0.9991756,0.00001187446,0.0001405978,0.0001769055,0.000234447,0.0002605447],"domain_scores_gemma":[0.9993888,0.00009925981,0.00004017972,0.0003514557,0.00004622371,0.0000740461],"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":[0.000004483453,0.0000272662,0.001306717,0.000003115499,0.00002408974,0.00003069538,0.0007057164,0.02383599,0.0006030916,0.9552886,0.002481435,0.01568879],"study_design_scores_gemma":[0.0007123906,0.0005751841,0.01946405,0.00001760776,0.000008943068,0.00004644213,0.0001721828,0.8578063,0.02553957,0.00369228,0.09126528,0.0006997209],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001938093,0.000006522531,0.7602589,0.0001380507,0.0001999228,0.00004703738,1.699853e-8,0.0003163817,0.2388394],"genre_scores_gemma":[0.525574,0.000001710581,0.4690603,0.0005419122,0.00004357845,6.09394e-7,2.079243e-7,0.000004321103,0.004773354],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9515963,"threshold_uncertainty_score":0.6106939,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01648638832331079,"score_gpt":0.2496534226924639,"score_spread":0.2331670343691531,"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."}}