{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:15:41Z","timestamp":1740100541232,"version":"3.37.3"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010663","name":"European Research Council (ERC)","doi-asserted-by":"publisher","award":["STG2018 804636"],"award-info":[{"award-number":["STG2018 804636"]}],"id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9687856","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"969-976","source":"Crossref","is-referenced-by-count":2,"title":["What does the User Want? Information Gain for Hierarchical Dialogue Policy Optimisation"],"prefix":"10.1109","author":[{"given":"C.","family":"Geishauser","sequence":"first","affiliation":[{"name":"Heinrich Heine University,Düsseldorf,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S.","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Cambridge,Department of Computer Science and Technology,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"H.","family":"Lin","sequence":"additional","affiliation":[{"name":"Heinrich Heine University,Düsseldorf,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"N.","family":"Lubis","sequence":"additional","affiliation":[{"name":"Heinrich Heine University,Düsseldorf,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M.","family":"Heck","sequence":"additional","affiliation":[{"name":"Heinrich Heine University,Düsseldorf,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S.","family":"Feng","sequence":"additional","affiliation":[{"name":"Heinrich Heine University,Düsseldorf,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C.","family":"van Niekerk","sequence":"additional","affiliation":[{"name":"Heinrich Heine University,Düsseldorf,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M.","family":"Gasic","sequence":"additional","affiliation":[{"name":"Heinrich Heine University,Düsseldorf,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","first-page":"3","author":"young","year":"2016","journal-title":"Evaluation of Statistical POMDP-Based Dialogue Systems in Noisy Environments"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5028"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-4013"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref10","article-title":"Challenges of real-world reinforcement learning","author":"dulac-arnold","year":"2019","journal-title":"Reinforcement Learning for Real Life (RL4RealLife) Workshop in the 36th International Conference on Machine Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-4095-0_7"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref13","article-title":"Feudal reinforcement learning","volume":"5","author":"dayan","year":"1993","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2112"},{"key":"ref15","volume":"abs 1711 11023","author":"casanueva","year":"2018","journal-title":"A benchmarking environment for reinforcement learning based task oriented dialogue management"},{"key":"ref16","article-title":"Dialog policy learning for joint clarification and active learning queries","author":"padmakumar","year":"2021","journal-title":"AAAI Conf on Artif Intell (AAAI)"},{"key":"ref17","article-title":"Learning database content for spoken dialogue system design","author":"polifroni","year":"2006","journal-title":"Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC'06)"},{"key":"ref18","article-title":"Domain directed dialogs for decision processes","volume":"abs cs 703072","author":"fodor","year":"2007","journal-title":"CoRR"},{"key":"ref19","article-title":"Vime: Variational information maximizing exploration","volume":"29","author":"houthooft","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5038"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-020-1692-3"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2851664"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2006.06.008"},{"key":"ref6","article-title":"Diluted near-optimal expert demonstrations for guiding dialogue stochastic policy optimisation","author":"cordier","year":"2020","journal-title":"34th Conference on Neural Information Processing Systems (NeurIPS 2020)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3013392"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.41"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3115\/1075218.1075231"},{"key":"ref9","article-title":"Sample efficient actorcritic with experience replay","author":"wang","year":"0","journal-title":"5th International Conference on Learning Representations ICLR 2017 Toulon France April 24–26 2017 Conference Track Proceedings"},{"key":"ref1","first-page":"1883","article-title":"A stochastic model of computer-human interaction for learning dialogue strategies","author":"levin","year":"0","journal-title":"Eurospeech 97"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11946","article-title":"BBQ-networks: Efficient exploration in deep reinforcement learning for task-oriented dialogue systems","volume":"32","author":"lipton","year":"2018","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref22","article-title":"Answerer in questioner's mind: Information theoretic approach to goal-oriented visual dialog","volume":"31","author":"lee","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Learning intrinsically motivated options to stimulate policy exploration","author":"bagot","year":"2020","journal-title":"Proceedings of the 37th International Conference on Machine Learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01346"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1646"},{"key":"ref26","article-title":"Noisy networks for exploration","author":"fortunato","year":"2018","journal-title":"Proceedings of the International Conference on Representation Learning (ICLR 2018)"},{"key":"ref25","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"0","journal-title":"Proceedings of the 33rd International Conference on Machine Learning - Volume 48 2016 ICML'16"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2021,12,13]]},"location":"Cartagena, Colombia","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09687856.pdf?arnumber=9687856","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,17]],"date-time":"2024-09-17T21:11:39Z","timestamp":1726607499000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9687856\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9687856","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}