{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:05:42Z","timestamp":1775837142162,"version":"3.50.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Science and Technology Council, Taiwan","award":["111-2634-F-A49-012"],"award-info":[{"award-number":["111-2634-F-A49-012"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3235202","type":"journal-article","created":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T19:57:36Z","timestamp":1673294256000},"page":"748-761","source":"Crossref","is-referenced-by-count":19,"title":["Hierarchical Reinforcement Learning With Guidance for Multi-Domain Dialogue Policy"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8417-2165","authenticated-orcid":false,"given":"Mahdin","family":"Rohmatillah","sequence":"first","affiliation":[{"name":"EECS International Graduate Program, National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3466-8941","authenticated-orcid":false,"given":"Jen-Tzung","family":"Chien","sequence":"additional","affiliation":[{"name":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6507"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1360"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1123"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746696"},{"issue":"8","key":"ref5","first-page":"1","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35142-6_14"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.sigdial-1.37"},{"key":"ref8","article-title":"Multi-domain task completion dialog challenge 2 at DSTC9","volume-title":"Proc. AAAI Workshop Dialog Syst. Technol. Challenge","author":"Li","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.41"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3013392"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2851664"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-534"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"},{"key":"ref14","first-page":"2564","article-title":"Fighting copycat agents in behavioral cloning from observation histories","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Wen","year":"2020"},{"key":"ref15","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-3006"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/1117562.1117565"},{"key":"ref18","article-title":"Learning end-to-end goal-oriented dialog","author":"Bordes","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271683"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-4013"},{"key":"ref21","article-title":"MultiWOZ 2.1: Multi-domain dialogue state corrections and state tracking baselines","author":"Eric","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.19"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414586"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5602"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-1042"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1133"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.23919\/Eusipco47968.2020.9287440"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1313"},{"key":"ref29","article-title":"Learning robust rewards with adversarial inverse reinforcement learning","author":"Fu","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1010"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.209"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688234"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1203"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017289"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.273"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17674"},{"key":"ref39","article-title":"Offline reinforcement learning for end-to-end task-oriented dialogue system","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jang","year":"2022"},{"key":"ref40","article-title":"A hybrid task-oriented dialog system with domain and task adaptive pretraining","author":"Zhang","year":"2021"},{"key":"ref41","article-title":"AuGPT: Dialogue with pre-trained language models and data augmentation","author":"Kulhnek","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482333"},{"key":"ref43","first-page":"424","article-title":"AVAST: Attentive variational state tracker in a reinforced navigator","volume-title":"Proc. Int. Joint Conf. Natural Lang. Process.","author":"Jang","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.283"},{"key":"ref45","first-page":"3307","article-title":"Data-efficient hierarchical reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Nachum","year":"2018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref47","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schulman","year":"2016"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000037"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1547"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.59"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.4135\/9781412983907.n1717"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref53","first-page":"2028","article-title":"Model-based soft actor-critic","volume-title":"Proc. Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf.","author":"Chien","year":"2021"},{"key":"ref54","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref55","first-page":"7768","article-title":"Critic regularized regression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2020"},{"key":"ref56","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen","year":"2021"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6394"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1233"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1459"},{"issue":"11","key":"ref60","first-page":"2579","article-title":"Visualizing data using $t$-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10011569.pdf?arnumber=10011569","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T07:55:45Z","timestamp":1707465345000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10011569\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3235202","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}