{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:18:29Z","timestamp":1763191109897,"version":"3.45.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227830","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Reward Fusion: Learning from Other Policies through Distillation"],"prefix":"10.1109","author":[{"given":"Yiwen","family":"Zhu","sequence":"first","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}]},{"given":"Jinyi","family":"Liu","sequence":"additional","affiliation":[{"name":"Tianjin University,China"}]},{"given":"Wenya","family":"Wei","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}]},{"given":"Zhou","family":"Fang","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103535"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(94)90047-7"},{"key":"ref3","first-page":"463","article-title":"Learning to drive a bicycle using reinforcement learning and shaping","volume-title":"ICML","volume":"98","author":"Randl\u00f8v"},{"key":"ref4","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Icml","volume":"99","author":"Ng"},{"key":"ref5","first-page":"433","article-title":"Dynamic potential-based reward shaping","volume-title":"Proceedings of the 11th international conference on autonomous agents and multiagent systems","author":"Devlin"},{"key":"ref6","first-page":"17","article-title":"Learning potential for reward shaping in reinforcement learning with tile coding","volume-title":"Proceedings AAMAS 2008 Workshop on Adaptive and Learning Agents and Multi-Agent Systems (ALAMAS-ALAg 2008)","author":"Grzes"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9628"},{"key":"ref8","first-page":"792","article-title":"Principled methods for advising reinforcement learning agents","volume-title":"Proceedings of the 20th international conference on machine learning (ICML-03)","author":"Wiewiora"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273572"},{"key":"ref10","first-page":"15931","article-title":"Learning to utilize shaping rewards: A new approach of reward shaping","volume":"33","author":"Hu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/324"},{"key":"ref12","article-title":"Hybrid reward architecture for reinforcement learning","volume":"30","author":"Van Seijen","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","first-page":"11298","article-title":"Rd\u02c62: Reward decomposition with representation decomposition","volume":"33","author":"Lin","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10827"},{"key":"ref15","first-page":"7436","article-title":"Uncertainty-based offline reinforcement learning with diversified q-ensemble","volume":"34","author":"An","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref17","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"International conference on machine learning","author":"Haarnoja"},{"article-title":"Soft actor-critic algorithms and applications","year":"2018","author":"Haarnoja","key":"ref18"},{"article-title":"Optimizing reward models with proximal policy exploration in preference-based reinforcement learning","volume-title":"NeurIPS 2024 Workshop on Behavioral Machine Learning","author":"Zhu","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29303"},{"key":"ref21","first-page":"5725","article-title":"vmfer: Von mises-fisher experience resampling based on uncertainty of gradient directions for policy improvement","volume-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","author":"Zhu"},{"key":"ref22","first-page":"440","article-title":"The influence of reward on the speed of reinforcement learning: An analysis of shaping","volume-title":"Proceedings of the 20th International Conference on Machine Learning (ICML-03)","author":"Laud"},{"article-title":"Enhancing robotic manipulation with ai feedback from multimodal large language models","year":"2024","author":"Liu","key":"ref23"},{"key":"ref24","first-page":"225","article-title":"Theoretical considerations of potential-based reward shaping for multi-agent systems","volume-title":"The 10th International Conference on Autonomous Agents and Multiagent Systems","author":"Devlin"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278759"},{"key":"ref26","first-page":"23417","article-title":"Individual reward assisted multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11741"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11498"},{"article-title":"Reward shaping via metalearning","year":"2019","author":"Zou","key":"ref29"},{"key":"ref30","first-page":"761","article-title":"Horde: A scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction","volume-title":"The 10th International Conference on Autonomous Agents and Multiagent SystemsVolume 2","author":"Sutton"},{"key":"ref31","first-page":"1104","article-title":"Exploiting structure in policy construction","volume-title":"IJCAI","volume":"14","author":"Boutilier"},{"key":"ref32","volume-title":"A survey of matrix theory and matrix inequalities","volume":"14","author":"Marcus","year":"1992"},{"article-title":"Real and complex analysis (mcgraw-hill international editions: Mathematics series)","year":"1987","author":"Rudin","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719574"},{"volume-title":"Reinforcement learning: An introduction","year":"2018","author":"Sutton","key":"ref35"},{"key":"ref36","first-page":"2601","article-title":"Where do rewards come from","volume-title":"Proceedings of the annual conference of the cognitive science society","author":"Singh"},{"article-title":"Openai gym","year":"2016","author":"Brockman","key":"ref37"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref38"},{"key":"ref39","article-title":"A generalized algorithm for multi-objective reinforcement learning and policy adaptation","volume":"32","author":"Yang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227830.pdf?arnumber=11227830","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:15:50Z","timestamp":1763190950000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227830\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227830","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}