{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:40:09Z","timestamp":1766061609797,"version":"3.48.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11245903","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"17454-17461","source":"Crossref","is-referenced-by-count":0,"title":["Successor Features for Transfer in Alternating Markov Games"],"prefix":"10.1109","author":[{"given":"Sunny","family":"Amatya","sequence":"first","affiliation":[{"name":"Arizona State University,School of Manufacturing Systems and Networks,Mesa,AZ,USA,85212"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Ren","sequence":"additional","affiliation":[{"name":"Arizona State University,School for Engineering of Matter, Transport, and Energy,Tempe,AZ,USA,85287"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Xu","sequence":"additional","affiliation":[{"name":"Arizona State University,School for Engineering of Matter, Transport, and Energy,Tempe,AZ,USA,85287"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenlong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Arizona State University,School of Manufacturing Systems and Networks,Mesa,AZ,USA,85212"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/app11114948"},{"article-title":"Emergent tool use from multi-agent autocurricula","year":"2019","author":"Baker","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00879-7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11396"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23919\/ACC53348.2022.9867155"},{"key":"ref6","first-page":"725","article-title":"Learning inter-task transferability in the absence of target task samples","volume-title":"Proceedings of the 2015 international conference on autonomous agents and multiagent systems","author":"Sinapov"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v12i1.12870"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9428"},{"key":"ref9","first-page":"322","article-title":"Friend-or-foe q-learning in general-sum games","volume-title":"Proceedings of the International Conference on Machine Learning","volume":"1","author":"Littman"},{"key":"ref10","article-title":"Successor features for transfer in reinforcement learning","volume":"30","author":"Barreto","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.105809"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v32i1.2332"},{"key":"ref13","first-page":"1041","article-title":"Transfer learning in real-time strategy games using hybrid cbr\/rl","volume-title":"IJCAI","volume":"7","author":"Sharma"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/DDCLS.2017.8068163"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/65"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561079"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2349152"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1907370117"},{"key":"ref19","first-page":"17 298","article-title":"Risk-aware transfer in reinforcement learning using successor features","volume":"34","author":"Gimelfarb","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","first-page":"1","article-title":"A new representation of successor features for transfer across dissimilar environments","volume-title":"International Conference on Machine Learning","author":"Abdolshah"},{"key":"ref21","article-title":"Generalized markov decision processes: Dynamic-programming and reinforcement-learning algorithms","volume-title":"Proceedings of International Conference of Machine Learning","volume":"96","author":"Szepesv\u00e1ri"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref23","volume-title":"Dynamic programming and optimal control: Volume I","volume":"4","author":"Bertsekas","year":"2012"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3041469"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1017\/9781009002127.013"},{"volume-title":"Neuro-dynamic programming","year":"1996","author":"Bertsekas","key":"ref26"},{"article-title":"Finite-time analysis of minimax q-learning for two-player zero-sum markov games: Switching system approach","year":"2023","author":"Lee","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2010.03.007"},{"article-title":"On evaluation of embodied navigation agents","year":"2018","author":"Anderson","key":"ref29"},{"article-title":"Advantages and limitations of using successor features for transfer in reinforcement learning","year":"2017","author":"Lehnert","key":"ref30"},{"key":"ref31","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref32","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Conference on robot learning","author":"Yu"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11245903.pdf?arnumber=11245903","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:35:33Z","timestamp":1766061333000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11245903\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11245903","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}