Hybrid Reinforcement/Supervised Learning of Dialogue Policies from Fixed Data Sets
Author:
Affiliation:
1. * Université de Genèave, Département d'Informatique, Battelle-bâtiment A, 7 route de Drize, 1227 Carouge, Switzerland..
2. ** University of Edinburgh, 2 Buccleuch Place, Edinburgh EH8 9LW, UK., .
Abstract
Publisher
MIT Press - Journals
Subject
Artificial Intelligence,Computer Science Applications,Linguistics and Language,Language and Linguistics
Link
https://www.mitpressjournals.org/doi/pdf/10.1162/coli.2008.07-028-R2-05-82
Reference9 articles.
1. Information state and dialogue management in the TRINDI dialogue move engine toolkit
2. A stochastic model of human-machine interaction for learning dialog strategies
3. A probabilistic framework for dialog simulation and optimal strategy learning
4. A survey of statistical user simulation techniques for reinforcement-learning of dialogue management strategies
Cited by 52 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. ORLEP: an efficient offline reinforcement learning evaluation platform;Multimedia Tools and Applications;2023-09-22
2. A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-oriented Dialogue Policy Learning;Machine Intelligence Research;2023-01-07
3. Lost in Dialogue: A Review and Categorisation of Current Dialogue System Approaches and Technical Solutions;KI 2023: Advances in Artificial Intelligence;2023
4. Conversational QA over Knowledge Bases;Neural Approaches to Conversational Information Retrieval;2023
5. Conversational AI for multi-agent communication in Natural Language;AI Communications;2022-09-30
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3