{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:03:53Z","timestamp":1764403433665,"version":"3.33.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,3]]},"DOI":"10.1109\/apsipaasc63619.2025.10849064","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:37:05Z","timestamp":1738003025000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Empathetic Response Generation via Regularized Q-Learning"],"prefix":"10.1109","author":[{"given":"Jen-Tzung","family":"Chien","sequence":"first","affiliation":[{"name":"National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Hsinchu,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi-Chien","family":"Wu","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Hsinchu,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Offline reinforcement learning for mixture-of-expert dialogue management","volume":"36","author":"Gupta","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414586"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1127"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24942-6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1256"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.327"},{"key":"ref7","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. of International Conference on Machine Learning","author":"Fujimoto"},{"key":"ref8","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume":"32","author":"Kumar","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","article-title":"A minimalist approach to offline reinforcement learning","volume":"34","author":"Fujimoto","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","first-page":"14129","article-title":"MOPO: Model-based offline policy optimization","volume":"33","author":"Yu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","first-page":"28954","article-title":"COMBO: Conservative offline model-based policy optimization","volume":"34","author":"Yu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018","journal-title":"OpenAI blog"},{"key":"ref14","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref15","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111201"},{"key":"ref17","first-page":"180","article-title":"Constructing the affective lexicon ontology","volume":"27","author":"Xu","year":"2008","journal-title":"Journal of China Society for Scientific and Technical Information"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206667"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11325"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016191"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60450-9_8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1061"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n16-1014"}],"event":{"name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2024,12,3]]},"location":"Macau, Macao","end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10848542\/10848533\/10849064.pdf?arnumber=10849064","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:24:19Z","timestamp":1738045459000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10849064\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc63619.2025.10849064","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}