{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T17:45:13Z","timestamp":1755798313784,"version":"3.44.0"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276047"],"award-info":[{"award-number":["62276047"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019065","name":"Sichuan Science and Technology Program","doi-asserted-by":"publisher","award":["2024JDRC0055"],"award-info":[{"award-number":["2024JDRC0055"]}],"id":[{"id":"10.13039\/501100019065","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Consumer Electron."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tce.2024.3476109","type":"journal-article","created":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T13:37:17Z","timestamp":1728394637000},"page":"5513-5522","source":"Crossref","is-referenced-by-count":2,"title":["Hands-Free: Action Abstraction With Hierarchical Reinforcement Learning in Text-Based Games"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4634-7961","authenticated-orcid":false,"given":"Anjie","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"given":"Hongcai","family":"He","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9561-8764","authenticated-orcid":false,"given":"Yongjun","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7801-0378","authenticated-orcid":false,"given":"Zetao","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2615-1555","authenticated-orcid":false,"given":"Jie","family":"Shao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3377377"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3306206"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2018.2859629"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3279869"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6297"},{"key":"ref6","first-page":"1","article-title":"Grounding physical concepts of objects and events through dynamic visual reasoning","volume-title":"Proc. 9th Int. Conf. Learn. Represent. (ICLR)","author":"Chen"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3207346"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04328-z"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00495"},{"key":"ref10","first-page":"1","article-title":"Graph constrained reinforcement learning for natural language action spaces","volume-title":"Proc. 8th Int. Conf. Learn. Represent. (ICLR)","author":"Ammanabrolu"},{"key":"ref11","first-page":"3566","article-title":"Learn what not to learn: Action elimination with deep reinforcement learning","volume-title":"Proc. 32nd Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Zahavy"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5857"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1358"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.704"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.50"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-023-05022-4"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6228"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.41"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.116"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1001"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1153"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.624"},{"key":"ref24","first-page":"1","article-title":"Learning dynamic belief graphs to generalize on text-based games","volume-title":"Proc. 34th Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Adhikari"},{"key":"ref25","first-page":"1","article-title":"Deep reinforcement learning with stacked hierarchical attention for text-based games","volume-title":"Proc. 34th Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Xu"},{"key":"ref26","first-page":"1","article-title":"Learning object-oriented dynamics for planning from text","volume-title":"Proc. 10th Int. Conf. Learn. Represent. (ICLR)","author":"Liu"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.187"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref31","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"}],"container-title":["IEEE Transactions on Consumer Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/30\/11128999\/10707323.pdf?arnumber=10707323","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T05:06:18Z","timestamp":1755579978000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10707323\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":31,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tce.2024.3476109","relation":{},"ISSN":["0098-3063","1558-4127"],"issn-type":[{"type":"print","value":"0098-3063"},{"type":"electronic","value":"1558-4127"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}