{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001020264,0.0001278046,0.0002140376,0.0005407439,0.000172164,0.0001108421,0.002210932,0.0001486557,0.00002015025],"category_scores_gemma":[0.0005681587,0.00009043097,0.0001226695,0.0003284289,0.0001104382,0.000343515,0.0004222135,0.0005680202,0.00009507399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008958462,"about_ca_system_score_gemma":0.0000574381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003744574,"about_ca_topic_score_gemma":0.00001402943,"domain_scores_codex":[0.9983177,0.000113314,0.0005220455,0.0001922729,0.0006307104,0.0002239559],"domain_scores_gemma":[0.9983395,0.0001342863,0.0005779582,0.000303365,0.000585362,0.00005955364],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002357017,0.0002487753,0.01787568,0.000008288701,0.0005571417,0.0002564986,0.0004661209,0.0005704037,0.02606458,0.2707057,0.01723238,0.6657787],"study_design_scores_gemma":[0.00172188,0.001302117,0.005123965,0.0001363903,0.0000275207,0.003293004,0.0001441236,0.003039317,0.01393683,0.08650152,0.8844827,0.0002906403],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5561238,0.0004550967,0.3638945,0.0556067,0.01773783,0.0002116076,0.000003179053,0.0003906203,0.005576635],"genre_scores_gemma":[0.9933823,0.00003619267,0.004629279,0.0004045625,0.001208655,0.000003440711,0.000003529545,0.00000905379,0.0003229858],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8672503,"threshold_uncertainty_score":0.4108499,"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."}}