{"id":"W2998085019","doi":"10.1609/aaai.v34i05.6308","title":"Bayes-Adaptive Monte-Carlo Planning and Learning for Goal-Oriented Dialogues","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Iran Telecommunication Research Center; Ministry of Science and ICT, South Korea; Ministry of Trade, Industry and Energy; National Research Foundation","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Machine learning; Task (project management); Negotiation; Bayesian probability; Bayes' theorem; Domain (mathematical analysis); 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":[0.0003987362,0.0002062397,0.0002725948,0.00006542861,0.0002831241,0.0001974255,0.001002067,0.00007734024,0.000004955955],"category_scores_gemma":[0.001057576,0.0001658002,0.00008850532,0.0003370479,0.0001459249,0.0004069516,0.0004269585,0.0003715677,0.000008258758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002328459,"about_ca_system_score_gemma":0.00005345184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002883527,"about_ca_topic_score_gemma":0.000002286413,"domain_scores_codex":[0.9983278,0.0000218122,0.0004219893,0.0005946538,0.0003121849,0.0003215583],"domain_scores_gemma":[0.9988009,0.0002007143,0.0002928596,0.0001424624,0.000435995,0.0001271033],"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":[0.000200519,0.0000478626,0.001200824,0.00007932937,0.00003130506,8.346688e-7,0.01806952,0.002952057,0.02126011,0.870444,0.00008534608,0.08562827],"study_design_scores_gemma":[0.00004720608,0.0004068774,0.0001265088,0.0001625093,0.00001228716,0.00000168011,0.001854655,0.8909321,0.08022455,0.02584002,0.0001855167,0.0002060739],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2223981,0.0000914336,0.7679248,0.006467239,0.0003055471,0.0006609263,0.000003980229,0.0001915254,0.001956364],"genre_scores_gemma":[0.982198,0.00001183979,0.01722736,0.0003436511,0.0001128801,0.00003387922,2.521876e-7,0.00001268402,0.00005946887],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.88798,"threshold_uncertainty_score":0.6761136,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1257072937796065,"score_gpt":0.2927804837799157,"score_spread":0.1670731900003092,"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."}}