{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:37:33Z","timestamp":1757608653076,"version":"3.44.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128043","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Simplifying Reward Design in Complex Robotics: Average-Reward Maximum Entropy Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Jean Seong Bjorn","family":"Choe","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, Korea University,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bumkyu","family":"Choi","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea University,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jong-kook","family":"Kim","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea University,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A brief survey of deep reinforcement learning","author":"Arulkumaran","year":"2017","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09997-9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref4","article-title":"Highdimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref6","article-title":"End-toend robotic reinforcement learning without reward engineering","author":"Singh","year":"2019","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3501710.3524734"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2023.3341257"},{"journal-title":"Reinforcement learning: An introduction. MIT press","year":"2018","author":"Sutton","key":"ref9"},{"key":"ref10","article-title":"Maximum entropy rl (provably) solves some robust rl problems","volume-title":"10th International Conference on Learning Representations, ICLR 2022","author":"Eysenbach","year":"2022"},{"volume-title":"Modeling purposeful adaptive behavior with the principle of maximum causal entropy","year":"2010","author":"Ziebart","key":"ref11"},{"key":"ref12","article-title":"Maximum entropy on-policy actor-critic via entropy advantage estimation","volume-title":"Seventeenth European Workshop on Reinforcement Learning","author":"Choe","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref14","first-page":"12535","article-title":"On-policy deep reinforcement learning for the average-reward criterion","volume-title":"International Conference on Machine Learning. PMLR","author":"Zhang","year":"2021"},{"key":"ref15","first-page":"1889","article-title":"Trust region policy optimization","author":"Schulman","year":"2015","journal-title":"International conference on machine learning. PMLR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/385"},{"key":"ref17","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/1043"},{"key":"ref19","article-title":"Realaigym: Education and research platform for studying athletic intelligence","volume-title":"Proceedings of Robotics Science and Systems Workshop Mind the Gap: Opportunities and Challenges in the Transition Between Research and Industry","author":"Wiebe","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3184837"},{"volume-title":"Markov decision processes: discrete stochastic dynamic programming","year":"2014","author":"Puterman","key":"ref21"},{"key":"ref22","article-title":"Average-reward model-free reinforcement learning: a systematic review and literature mapping","author":"Dewanto","year":"2020","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Reinforcement learning and control as probabilistic inference: Tutorial and review","author":"Levine","year":"2018","journal-title":"arXiv preprint"},{"key":"ref24","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016","journal-title":"International conference on machine learning. PMLR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2922583"},{"key":"ref26","article-title":"Solving the swingup and balance task for the acrobot and pendubot with sac","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"What matters for on-policy deep actor-critic methods? a large-scale study","volume-title":"International conference on learning representations","author":"Andrychowicz","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2023.3341257"},{"key":"ref29","article-title":"Crossq: Batch normalization in deep reinforcement learning for greater sample efficiency and simplicity","volume-title":"The Twelfth International Conference on Learning Representations","author":"Bhatt","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560990"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128043.pdf?arnumber=11128043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:15:23Z","timestamp":1756880123000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128043\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128043","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}