{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T14:58:33Z","timestamp":1742396313800},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053235","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"8024-8028","source":"Crossref","is-referenced-by-count":3,"title":["Improving Sample-Efficiency in Reinforcement Learning for Dialogue Systems by Using Trainable-Action-Mask"],"prefix":"10.1109","author":[{"given":"Yen-Chen","family":"Wu","sequence":"first","affiliation":[]},{"given":"Bo-Hsiang","family":"Tseng","sequence":"additional","affiliation":[]},{"given":"Carl Edward","family":"Rasmussen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"The predictron: End-to-end learning and planning","year":"2016","author":"silver","key":"ref10"},{"key":"ref11","first-page":"2829","article-title":"Continuous deep q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref13","first-page":"6118","article-title":"Value prediction network","author":"oh","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"article-title":"Dyna-style planning with linear function approximation and prioritized sweeping","year":"2012","author":"sutton","key":"ref15"},{"article-title":"Integrating planning for taskcompletion dialogue policy learning","year":"2018","author":"peng","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1416"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-4013"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/1614108.1614146"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2225812"},{"key":"ref3","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163950"},{"article-title":"A benchmarking environment for reinforcement learning based task oriented dialogue management","year":"2017","author":"casanueva","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1230"},{"article-title":"Dialogue learning with human-in-the-loop","year":"2016","author":"li","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref1"},{"key":"ref9","first-page":"2154","article-title":"Value iteration networks","author":"tamar","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2012071"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053235.pdf?arnumber=9053235","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:09:00Z","timestamp":1656374940000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053235\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053235","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}