{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:45:45Z","timestamp":1750308345316,"version":"3.41.0"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Postdoctoral Fellowship Program of China Postdoctoral Science Foundation","award":["GZC20232995"],"award-info":[{"award-number":["GZC20232995"]}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tg.2024.3450475","type":"journal-article","created":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T18:11:42Z","timestamp":1724955102000},"page":"334-345","source":"Crossref","is-referenced-by-count":0,"title":["Learning Individual Potential-Based Rewards in Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9105-4087","authenticated-orcid":false,"given":"Chen","family":"Yang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1766-5634","authenticated-orcid":false,"given":"Pei","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9970-394X","authenticated-orcid":false,"given":"Junge","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","year":"2016","author":"Shalev-Shwartz","key":"ref1"},{"article-title":"Smarts: Scalable multi-agent reinforcement learning training school for autonomous driving","year":"2020","author":"Zhou","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102861"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207663"},{"article-title":"Guided deep reinforcement learning for swarm systems","year":"2017","author":"Httenrauch","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3184795"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3129504"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3023733"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref10","first-page":"1151","article-title":"Multi-agent reinforcement learning for traffic light control","volume-title":"Proc. 17th Int. Conf. Mach. Learn.","author":"Wiering","year":"2000"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3036962"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3072435"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2022.3223926"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2021.3134259"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2023.3236065"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2022.3228401"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v16i1.7416"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2022.3169168"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2022.3226910"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/37"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2021.3113313"},{"key":"ref22","first-page":"807","article-title":"All learning is local: Multi-agent learning in global reward games","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chang","year":"2003"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref24","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative, multi-agent games","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yu","year":"2022"},{"key":"ref25","first-page":"4295","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid","year":"2018"},{"article-title":"Qatten: A general framework for cooperative multiagent reinforcement learning","year":"2020","author":"Yang","key":"ref26"},{"key":"ref27","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ng","year":"1999"},{"key":"ref28","first-page":"463","article-title":"Learning to drive a bicycle using reinforcement learning and shaping","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Randlv","year":"1998"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1329125.1329434"},{"key":"ref30","first-page":"165","article-title":"Potential-based difference rewards for multiagent reinforcement learning","volume-title":"Proc. 2014 Int. Conf. Auton. Agents Multi-Agent Syst.","author":"Devlin","year":"2014"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206879"},{"key":"ref32","first-page":"521","article-title":"Local approximation of difference evaluation functions","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst.","author":"Colby","year":"2016"},{"key":"ref33","first-page":"4649","article-title":"On learning intrinsic rewards for policy gradient methods","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zheng","year":"2018"},{"key":"ref34","first-page":"4403","article-title":"LIIR: Learning individual intrinsic reward in multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Du","year":"2019"},{"key":"ref35","first-page":"23417","article-title":"Individual reward assisted multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref36","first-page":"2418","article-title":"Learning individual difference rewards in multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst.","author":"Yang","year":"2023"},{"key":"ref37","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sutton","year":"1999"},{"key":"ref38","first-page":"980","article-title":"Deep coordination graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bhmer"},{"key":"ref39","first-page":"2186","article-title":"The StarCraft multi-agent challenge","volume-title":"Proc. 18th Int. Conf. Auton. Agents Multiagent Syst.","author":"Samvelyan","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref41","first-page":"227","article-title":"Coordinated reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guestrin","year":"2002"},{"key":"ref42","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2018"},{"key":"ref43","first-page":"330","article-title":"Multi-agent reinforcement learning: Independent versus cooperative agents","volume-title":"Proc. 10th Int. Conf. Mach. Learn.","author":"Tan","year":"1993"},{"article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","year":"2017","author":"Sunehag","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref47","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2021"},{"key":"ref48","first-page":"5887","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Son","year":"2019"},{"key":"ref49","first-page":"11853","article-title":"Learning implicit credit assignment for cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhou","year":"2020"},{"key":"ref50","article-title":"DOP: Off-policy multi-agent decomposed policy gradients","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2020"},{"key":"ref51","first-page":"1391","article-title":"Agent-temporal attention for reward redistribution in episodic multi-agent reinforcement learning","volume-title":"Proc. 21st Int. Conf. Auton. Agents Multiagent Syst.","author":"Xiao","year":"2022"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3384"},{"key":"ref53","first-page":"225","article-title":"Theoretical considerations of potential-based reward shaping for multi-agent systems","volume-title":"Proc. 10th Int. Conf. Auton. Agents Multiagent Syst.","author":"Devlin","year":"2011"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref55","first-page":"29","article-title":"Deep recurrent Q-learning for partially observable MDPs","volume-title":"Proc. 2015 AAAI Fall Symp. Ser.","author":"Hausknecht","year":"2015"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2447"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref57"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i10.26384"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/32"},{"key":"ref60","first-page":"792","article-title":"Principled methods for advising reinforcement learning agents","volume-title":"Proc. 20th Int. Conf. Mach. Learn.","author":"Wiewiora","year":"2003"},{"key":"ref61","first-page":"433","article-title":"Dynamic potential-based reward shaping","volume-title":"Proc. 11th Int. Conf. Auton. Agents Multiagent Syst.","author":"Devlin","year":"2012"},{"key":"ref62","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","volume-title":"Proc. NIPS Workshop Deep Learn.","author":"Chung","year":"2014"},{"key":"ref63","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schulman","year":"2016"},{"key":"ref64","article-title":"Rethinking the implementation tricks and monotonicity constraint in cooperative multi-agent reinforcement learning","volume-title":"Proc. 2nd Blogpost Track ICLR","author":"Hu","year":"2023"},{"key":"ref65","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7782673\/11038929\/10659352.pdf?arnumber=10659352","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T17:41:36Z","timestamp":1750268496000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10659352\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":65,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tg.2024.3450475","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"type":"print","value":"2475-1502"},{"type":"electronic","value":"2475-1510"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}