{"id":"W2015313388","doi":"10.1007/s10772-014-9224-x","title":"Dialogue POMDP components (Part II): learning the reward function","year":2014,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval","funders":"","keywords":"Partially observable Markov decision process; Computer science; Reinforcement learning; Markov decision process; Context (archaeology); Artificial intelligence; Function (biology); Process (computing); Bellman equation; Machine learning; Markov process; Markov chain; Markov model; Mathematical optimization; 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":[0.001477143,0.001027873,0.001128046,0.0003120274,0.000428394,0.001825099,0.00162563,0.00141272,0.01457134],"category_scores_gemma":[0.00714266,0.0007765064,0.0006933609,0.0003107325,0.0006595586,0.002063914,0.001744034,0.002621439,0.002030648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000931944,"about_ca_system_score_gemma":0.00193108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00431527,"about_ca_topic_score_gemma":0.003610569,"domain_scores_codex":[0.9992594,0.0001897971,0.00003864049,0.0002495947,0.0001620586,0.0001005701],"domain_scores_gemma":[0.9988332,0.0006058007,0.00005570961,0.0001946852,0.0002223561,0.00008824966],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001207897,0.000402938,0.003186737,0.00051843,0.0001735122,0.00020435,0.0005211631,0.3205005,0.02178867,0.05622165,0.007973084,0.5873011],"study_design_scores_gemma":[0.00007420477,0.0001712512,0.001161754,0.00004813558,0.00004682429,0.00005246509,0.00004672063,0.9512985,0.01252555,0.03045222,0.004086839,0.0000356071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01748937,0.000236401,0.9759453,0.0002595134,0.0001189754,0.000255304,0.000274823,0.001366075,0.004054229],"genre_scores_gemma":[0.5295138,0.0003040998,0.4580461,0.0002002034,0.000114979,0.0006686873,0.0007899718,0.0004900264,0.009872055],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01457134,"threshold_uncertainty_score":0.04874599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0121418797332161,"score_gpt":0.2309892475912225,"score_spread":0.2188473678580064,"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."}}