{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T05:13:27Z","timestamp":1744953207732,"version":"3.37.3"},"reference-count":23,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003696","name":"Electronics and Telecommunications Research Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003696","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["22ZR1100","2021R1F1A1048098"],"award-info":[{"award-number":["22ZR1100","2021R1F1A1048098"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1109\/lra.2022.3186508","type":"journal-article","created":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:29:36Z","timestamp":1656361776000},"page":"7858-7864","source":"Crossref","is-referenced-by-count":1,"title":["Utilizing Hidden Observations to Enhance the Performance of the Trained Agent"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6931-9592","authenticated-orcid":false,"given":"Sooyoung","family":"Jang","sequence":"first","affiliation":[{"name":"Intelligence Convergence Research Laboratory, Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1102-3905","authenticated-orcid":false,"given":"Joohyung","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Computing, Gachon University, Seongnam, South Korea"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1038\/nature14236"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1609\/aaai.v32i1.11694"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/LRA.2021.3097345"},{"issue":"2","key":"ref4","first-page":"1","article-title":"Prioritized environment configuration for drone control with deep reinforcement learning","volume":"12","author":"Jang","year":"2022","journal-title":"Hum.-Centric Comput. Inf. Sci."},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1201\/9781351006620-6"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/LRA.2017.2720851"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/LRA.2018.2869644"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1177\/0278364917710318"},{"year":"2019","author":"OpenAI","article-title":"Dota 2 with large scale deep reinforcement learning","key":"ref9"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1613\/jair.5699"},{"key":"ref11","first-page":"21810","article-title":"MOReL: Model-based offline reinforcement learning","volume-title":"Proc. 34th Conf. Neural Inf. Process. Syst.","author":"Kidambi","year":"2020"},{"key":"ref12","first-page":"29420","article-title":"Offline reinforcement learning with reverse model-based imagination","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Wang","year":"2021"},{"year":"2021","author":"Kalyanakrishnan","article-title":"An analysis of frame-skipping in reinforcement learning","key":"ref13"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1609\/aaai.v31i1.10918"},{"key":"ref15","article-title":"Learning to repeat: Fine grained action repetition for deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sharma","year":"2017"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/IROS.2012.6386109"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/JPROC.2017.2761740"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1016\/j.icte.2020.04.010"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1016\/S0893-6080(96)00098-6"},{"key":"ref20","article-title":"Unifying count-based exploration and intrinsic motivation","volume-title":"Proc. 30th Conf. Neural Inf. Process. Syst.","volume":"29","author":"Bellemare","year":"2016"},{"year":"2017","author":"Schulman","article-title":"Proximal policy optimization algorithms","key":"ref21"},{"year":"2016","author":"Brockman","article-title":"OpenAI gym","key":"ref22"},{"year":"2016","author":"Tan","article-title":"Continuous tasks and constraints transitions for the control of robots","key":"ref23"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9750005\/09807373.pdf?arnumber=9807373","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T04:47:57Z","timestamp":1706762877000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9807373\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":23,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2022.3186508","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"type":"electronic","value":"2377-3766"},{"type":"electronic","value":"2377-3774"}],"subject":[],"published":{"date-parts":[[2022,7]]}}}