{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T14:39:24Z","timestamp":1771511964525,"version":"3.50.1"},"reference-count":23,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2018,7,1]],"date-time":"2018-07-01T00:00:00Z","timestamp":1530403200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Basic Science Research Program"},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea (NRF)","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Ministry of Science and ICT","award":["(NRF-2017R1A2B2006136)"],"award-info":[{"award-number":["(NRF-2017R1A2B2006136)"]}]},{"name":"Next-Generation Information Computing Development Program"},{"name":"NRF"},{"name":"Ministry of Science and ICT","award":["(2017M3C4A7065926)"],"award-info":[{"award-number":["(2017M3C4A7065926)"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1109\/lra.2018.2800085","type":"journal-article","created":{"date-parts":[[2018,1,31]],"date-time":"2018-01-31T19:19:30Z","timestamp":1517426370000},"page":"1466-1473","source":"Crossref","is-referenced-by-count":25,"title":["Sparse Markov Decision Processes With Causal Sparse Tsallis Entropy Regularization for Reinforcement Learning"],"prefix":"10.1109","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0147-2715","authenticated-orcid":false,"given":"Kyungjae","family":"Lee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sungjoon","family":"Choi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9781-2018","authenticated-orcid":false,"given":"Songhwai","family":"Oh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.09.141"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7040156"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/BF01016429"},{"key":"ref13","article-title":"Projection onto the probability simplex: An efficient algorithm\n with a simple proof, and an application","author":"wang","year":"2013","journal-title":"arXiv preprint arXiv 1309 1541"},{"key":"ref14","volume":"66","author":"smart","year":"1980","journal-title":"Fixed Point Theorems"},{"key":"ref15","article-title":"Continuous control with deep reinforcement\n learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref16","author":"lee","year":"0"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1137\/S105262349834847X"},{"key":"ref18","article-title":"From softmax to sparsemax: A sparse model of attention and multi-label classification","author":"martins","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","article-title":"Modeling purposeful adaptive behavior with the principle of\n maximum causal entropy","author":"ziebart","year":"2010"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2720851"},{"key":"ref6","article-title":"Reinforcement learning with deep\n energy-based policies","author":"haarnoja","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref5","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"0","journal-title":"Proc 17th Int Conf Mach Learn"},{"key":"ref8","article-title":"Equivalence\n between policy gradients and soft q-learning","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1704 06440"},{"key":"ref7","article-title":"Actor-critic reinforcement learning with energy-based policies","author":"heess","year":"0","journal-title":"Proc of European Workshop on Reinforcement Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2013.6621824"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2014.6957722"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24455-1_33"},{"key":"ref20","article-title":"Prioritized experience\n replay","author":"schaul","year":"2015","journal-title":"arXiv preprint arXiv 1511 05271"},{"key":"ref22","first-page":"2094","article-title":"Deep\n reinforcement learning with double q-learning","author":"van hasselt","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022676722315"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/8302435\/08276246.pdf?arnumber=8276246","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:17:59Z","timestamp":1642004279000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8276246\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":23,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2018.2800085","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,7]]}}}