{"id":"W2112476714","doi":"10.1109/icassp.2011.5946754","title":"Bayesian reinforcement learning for POMDP-based dialogue systems","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Partially observable Markov decision process; Robustness (evolution); Artificial intelligence; Machine learning; Bayesian probability; Popularity; Domain (mathematical analysis); Markov chain","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":[0.002632847,0.0009569351,0.00152005,0.0004896031,0.0006523466,0.001345391,0.001453629,0.001221207,0.003036455],"category_scores_gemma":[0.009550112,0.0007532821,0.0008212387,0.0004588974,0.00190496,0.001730809,0.001860293,0.002372501,0.0005087403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002091849,"about_ca_system_score_gemma":0.002161638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009810604,"about_ca_topic_score_gemma":0.008466557,"domain_scores_codex":[0.9983966,0.0007288962,0.00008100928,0.0002247416,0.0004331851,0.0001355379],"domain_scores_gemma":[0.9966363,0.002555739,0.0002227566,0.0001430273,0.0002988291,0.0001433199],"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":[0.00004429592,0.00002594848,0.0001941761,0.00007436098,0.00002454004,0.00004771235,0.00006898108,0.948957,0.0004465673,0.03682766,0.0004666455,0.0128222],"study_design_scores_gemma":[0.000009037608,0.000007004667,0.00001944426,0.000004392062,0.000002765781,0.000004242177,0.000003736627,0.985087,0.00008846107,0.01450671,0.0002634334,0.000003663935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004579239,0.0002329539,0.9926287,0.0002010526,0.00002701729,0.00004007771,0.00003829304,0.0002962065,0.001956364],"genre_scores_gemma":[0.7118686,0.0005692958,0.2830317,0.0001740613,0.00008765933,0.0004014269,0.0002146762,0.0001655371,0.003487017],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009810604,"threshold_uncertainty_score":0.01950699,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03669384001913174,"score_gpt":0.2313896200382744,"score_spread":0.1946957800191426,"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."}}