{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T13:06:32Z","timestamp":1775912792597,"version":"3.50.1"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"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":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892798","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-7","source":"Crossref","is-referenced-by-count":4,"title":["Fast Probabilistic Policy Reuse via Reward Function Fitting"],"prefix":"10.1109","author":[{"given":"Jinmei","family":"Liu","sequence":"first","affiliation":[{"name":"Nanjing University,Department of Control and Systems Engineering,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing University,Department of Control and Systems Engineering,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunlin","family":"Chen","sequence":"additional","affiliation":[{"name":"Nanjing University,Department of Control and Systems Engineering,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927320"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.11.014"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11718"},{"key":"ref32","first-page":"468","article-title":"Measuring the distance between finite markov decision processes","author":"song","year":"0","journal-title":"Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems"},{"key":"ref31","article-title":"An automated measure of mdp similarity for transfer in reinforcement learning","author":"ammar","year":"0","journal-title":"Workshops at the Twenty-Eighth AAAI Conference on Artificial Intelligence"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10796"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"1772","DOI":"10.1109\/IJCNN.2001.938430","article-title":"Supervised learning with spiking neural networks","volume":"3","author":"xin","year":"2001","journal-title":"IJCNN'01 International Joint Conference on Neural Networks Proceedings (Cat No 01CH37222)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/72.536316"},{"key":"ref35","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"0","journal-title":"Proceedings of International Conference on Machine Learning"},{"key":"ref34","first-page":"52","article-title":"Supervised learning of probability distributions by neural networks","volume":"12","author":"baum","year":"1988","journal-title":"Neural Information Processing Systems"},{"key":"ref10","first-page":"6651","article-title":"Evolutionary reinforcement learning for sample-efficient multiagent coordination","volume":"119","author":"majumdar","year":"0","journal-title":"Proceedings of International Conference on Machine Learning"},{"key":"ref40","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"0","journal-title":"Proceedings of International Conference on Machine Learning"},{"key":"ref11","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_5"},{"key":"ref13","first-page":"15 146","article-title":"Knowledge transfer in multi-task deep reinforcement learning for continuous control","volume":"33","author":"xu","year":"0","journal-title":"Proceedings of Advances in Neural Information Processing Systems"},{"key":"ref14","first-page":"1","article-title":"A new representation of successor features for transfer across dissimilar environments","volume":"139","author":"abdolshah","year":"0","journal-title":"Proceedings of International Conference on Machine Learning"},{"key":"ref15","first-page":"4058","article-title":"Successor features for transfer in reinforcement learning","author":"barreto","year":"0","journal-title":"Proceedings of International Conference on Neural Information Processing Systems"},{"key":"ref16","first-page":"181","article-title":"Policy transfer using reward shaping","author":"brys","year":"0","journal-title":"AAMAS"},{"key":"ref17","article-title":"Learning invariant feature spaces to transfer skills with reinforcement learning","author":"gupta","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref18","article-title":"Actor-mimic: Deep multitask and transfer reinforcement learning","author":"parisotto","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390225"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref27","article-title":"Unsupervised cross-domain transfer in policy gradient reinforcement learning via manifold alignment","author":"ammar","year":"0","journal-title":"Twenty-Ninth AAAI Conference on Artificial Intelligence"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grand-master level in starcraft ii using multi-agent reinforcement learning","volume":"575","author":"vinyals","year":"2019","journal-title":"Nature"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-019-0804-2"},{"key":"ref29","first-page":"2555","article-title":"Transferring expectations in model-based reinforcement learning","volume":"25","author":"nguyen","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref8","article-title":"Improving sample efficiency in model-free reinforcement learning from images","author":"yarats","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref9","first-page":"7780","article-title":"Offline meta-reinforcement learning with advantage weighting","volume":"139","author":"mitchell","year":"0","journal-title":"Proceedings of International Conference on Machine Learning"},{"key":"ref1","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","article-title":"Adapting interaction environments to diverse users through online action set selection","author":"mahmud","year":"0","journal-title":"Workshops at the Twenty-Eighth AAAI Conference on Artificial Intelligence"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2010.03.007"},{"key":"ref21","first-page":"720","article-title":"Probabilistic policy reuse in a reinforcement learning agent","author":"fern\u00e1ndez","year":"0","journal-title":"Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_40"},{"key":"ref41","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref23","first-page":"10141","article-title":"Repaint: Knowledge transfer in deep reinforcement learning","volume":"139","author":"tao","year":"0","journal-title":"Proceedings of International Conference on Machine Learning"},{"key":"ref26","first-page":"21","article-title":"Reinforcement learning transfer via common subspaces","author":"ammar","year":"2011","journal-title":"Adaptive and Learning Agents Workshop"},{"key":"ref25","article-title":"Transfer learning via inter-task mappings for temporal difference learning","volume":"8","author":"taylor","year":"2007","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","location":"Padua, Italy","start":{"date-parts":[[2022,7,18]]},"end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892798.pdf?arnumber=9892798","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T20:52:58Z","timestamp":1665780778000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892798\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892798","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}