{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T14:03:12Z","timestamp":1756994592709,"version":"3.37.3"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,10,24]]},"DOI":"10.1109\/iros45743.2020.9341477","type":"proceedings-article","created":{"date-parts":[[2021,2,13]],"date-time":"2021-02-13T02:26:48Z","timestamp":1613183208000},"page":"5484-5489","source":"Crossref","is-referenced-by-count":1,"title":["TTR-Based Reward for Reinforcement Learning with Implicit Model Priors"],"prefix":"10.1109","author":[{"given":"Xubo","family":"Lyu","sequence":"first","affiliation":[{"name":"Simon Fraser University,School of Computing Science,CA,V5A1S6"}]},{"given":"Mo","family":"Chen","sequence":"additional","affiliation":[{"name":"Simon Fraser University,School of Computing Science,CA,V5A1S6"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ECC.2015.7331044"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798509"},{"key":"ref12","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2012.6426643"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2461328.2461359"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-012-9671-y"},{"journal-title":"Optimal Control and Viscosity Solutions of Hamilton-Jacobi-Bellman Equations","year":"2008","author":"bardi","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9947-1991-0991958-X"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-007-9174-4"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798268"},{"article-title":"Deep exploration via randomized value functions","year":"2017","author":"osband","key":"ref4"},{"key":"ref3","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Annual Int Conf Machine Learning"},{"key":"ref6","first-page":"3303","article-title":"Data-efficient hierarchical reinforcement learning","author":"nachum","year":"2018","journal-title":"Advances in neural information processing systems"},{"article-title":"Reverse curriculum generation for reinforcement learning","year":"2017","author":"florensa","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152834"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0468-y"},{"article-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref2"},{"key":"ref9","first-page":"465","article-title":"Pilco: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2797194"},{"article-title":"Ttr-based reward for reinforcement learning with implicit model priors","year":"2019","author":"lyu","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389727"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509627"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6631299"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989693"}],"event":{"name":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2020,10,24]]},"location":"Las Vegas, NV, USA","end":{"date-parts":[[2021,1,24]]}},"container-title":["2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9340668\/9340635\/09341477.pdf?arnumber=9341477","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:51:28Z","timestamp":1656453088000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9341477\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,24]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/iros45743.2020.9341477","relation":{},"subject":[],"published":{"date-parts":[[2020,10,24]]}}}