{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002595408,0.001276553,0.001656006,0.0007084392,0.0007786297,0.001706403,0.002120264,0.001685219,0.005930243],"category_scores_gemma":[0.008723672,0.0008309413,0.001201151,0.0008219366,0.001886307,0.002486642,0.001751124,0.002677372,0.0007026959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002106823,"about_ca_system_score_gemma":0.001830794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008398677,"about_ca_topic_score_gemma":0.007056301,"domain_scores_codex":[0.9981615,0.0006448966,0.0001248097,0.0003837694,0.0004983515,0.0001866658],"domain_scores_gemma":[0.9967999,0.002214917,0.0003331369,0.0002000338,0.0003054329,0.0001465089],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000698143,0.0000396915,0.0007856717,0.0001335031,0.00005144992,0.0001034609,0.0001207608,0.6881525,0.0003967959,0.2809283,0.001703215,0.02751478],"study_design_scores_gemma":[0.00002835617,0.0000151067,0.0000879245,0.00001571205,0.00001064695,0.00001879941,0.0000141343,0.8700805,0.0001220442,0.1276761,0.001920344,0.00001027521],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00903169,0.0005928862,0.9813363,0.0005365959,0.00007873564,0.00009037509,0.0002337702,0.0002885201,0.007811164],"genre_scores_gemma":[0.6138174,0.001532952,0.3729467,0.0003263998,0.0001595786,0.0005983475,0.0006304537,0.0001091214,0.009879159],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008398677,"threshold_uncertainty_score":0.01983863,"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."}}