{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T01:40:59Z","timestamp":1729647659000,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"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":[[2020,7]]},"DOI":"10.1109\/ijcnn48605.2020.9206954","type":"proceedings-article","created":{"date-parts":[[2020,9,30]],"date-time":"2020-09-30T00:40:33Z","timestamp":1601426433000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Transfer Learning based Task-oriented Dialogue Policy for Multiple Domains using Hierarchical Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Tulika","family":"Saha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sriparna","family":"Saha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pushpak","family":"Bhattacharyya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"arXiv preprint arXiv 1511 05952"},{"key":"ref11","first-page":"3776","article-title":"Building end-to-end dialogue systems using generative hierarchical neural network models","volume":"16","author":"serban","year":"2016","journal-title":"AAAI"},{"key":"ref12","article-title":"Learning end-to-end goal-oriented dialog","author":"bordes","year":"2016","journal-title":"arXiv preprint arXiv 1605 07683"},{"key":"ref13","article-title":"A neural conversational model","author":"vinyals","year":"2015","journal-title":"arXiv preprint arXiv 1506 08700"},{"key":"ref14","article-title":"Deep reinforcement learning for multi-domain dialogue systems","author":"cuay\u00e1huitl","year":"2016","journal-title":"arXiv preprint arXiv 1611 08675"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/572"},{"key":"ref16","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","author":"lipton","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref17","first-page":"733","article-title":"End-to-end task-completion neural dialogue systems","author":"li","year":"0"},{"key":"ref18","first-page":"556","article-title":"Intra-option learning about temporally abstract actions","volume":"98","author":"sutton","year":"1998","journal-title":"ICML"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1127"},{"key":"ref3","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"0"},{"key":"ref6","article-title":"End-to-end task-completion neural dialogue systems","author":"li","year":"2017","journal-title":"arXiv preprint arXiv 1703 01281"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2112"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1253"},{"key":"ref2","first-page":"438","article-title":"A network-based end-to-end trainable task-oriented dialogue system","author":"rojas-barahona","year":"0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1237"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/116580.116612"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref21","first-page":"207","article-title":"Frames: a corpus for adding memory to goal-oriented dialogue systems","author":"asri","year":"0"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1060","article-title":"Deep reinforcement learning of dialogue policies with less weight updates","author":"cuay\u00e1huitl","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.2307\/2332510"}],"event":{"name":"2020 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2020,7,19]]},"location":"Glasgow, United Kingdom","end":{"date-parts":[[2020,7,24]]}},"container-title":["2020 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9200848\/9206590\/09206954.pdf?arnumber=9206954","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T06:21:06Z","timestamp":1669011666000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9206954\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/ijcnn48605.2020.9206954","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}