{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002749465,0.0006975507,0.000947461,0.000502684,0.0005369973,0.0008129025,0.001516403,0.001217171,0.002504973],"category_scores_gemma":[0.01140078,0.0006478457,0.0005705731,0.0003881044,0.001344319,0.001307568,0.001273081,0.001757701,0.000445194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001349471,"about_ca_system_score_gemma":0.002030322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00784755,"about_ca_topic_score_gemma":0.008603603,"domain_scores_codex":[0.9986143,0.0007188705,0.00006416463,0.0002179167,0.0002758161,0.0001088523],"domain_scores_gemma":[0.99534,0.003732163,0.00023423,0.0002098605,0.000319283,0.0001644607],"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":[0.00009921494,0.00005322447,0.000654147,0.00005212015,0.0000274607,0.00005596499,0.0001228778,0.9440146,0.0008897332,0.02186439,0.0005385767,0.03162779],"study_design_scores_gemma":[0.000006145736,0.000006576701,0.00002685225,0.0000031374,0.000001828654,0.000004577889,0.000003382795,0.9928892,0.0001852951,0.006690155,0.000180499,0.000002400532],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01417584,0.0001515106,0.9830061,0.0002066026,0.00002905355,0.0000527234,0.00002586187,0.0003377271,0.002014613],"genre_scores_gemma":[0.6508335,0.0001733782,0.3460064,0.0002014359,0.00005187273,0.0002575195,0.0001239572,0.0001245309,0.002227364],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00784755,"threshold_uncertainty_score":0.01560372,"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."}}