{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:10:30Z","timestamp":1730247030611,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"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":[[2022,10,16]]},"DOI":"10.1109\/icip46576.2022.9897349","type":"proceedings-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T21:27:24Z","timestamp":1667510844000},"page":"991-995","source":"Crossref","is-referenced-by-count":1,"title":["Improving Generalization of Reinforcement Learning Using a Bilinear Policy Network"],"prefix":"10.1109","author":[{"given":"Fen","family":"Fang","sequence":"first","affiliation":[{"name":"A*STAR,Institute for Infocomm Research,Singapore"}]},{"given":"Wenyu","family":"Liang","sequence":"additional","affiliation":[{"name":"A*STAR,Institute for Infocomm Research,Singapore"}]},{"given":"Yan","family":"Wu","sequence":"additional","affiliation":[{"name":"A*STAR,Institute for Infocomm Research,Singapore"}]},{"given":"Qianli","family":"Xu","sequence":"additional","affiliation":[{"name":"A*STAR,Institute for Infocomm Research,Singapore"}]},{"given":"Joo-Hwee","family":"Lim","sequence":"additional","affiliation":[{"name":"A*STAR,Institute for Infocomm Research,Singapore"}]}],"member":"263","reference":[{"key":"ref1","first-page":"817","article-title":"State similarity based approach for improving performance in rl","volume-title":"Proceedings of the 20th International Joint Conference on Artificial Intelligence","author":"Sertan"},{"article-title":"Contrastive behavioral similarity embeddings for generalization in reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Agarwal","key":"ref2"},{"key":"ref3","article-title":"Bilinear classifiers for visual recognition","volume":"22","author":"Hamed","year":"2009","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296694"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA.2017.8227411"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2017.8037745"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-020-02283-z"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_11"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790410"},{"key":"ref11","first-page":"1038","article-title":"Bi-linear value networks for multi-goal reinforcement learning","volume-title":"In International Conference on Machine Learning","author":"Hong"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/4175.001.0001"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299194"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.128"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref16","first-page":"1038","article-title":"Generalization in reinforcement learning: Successful examples using sparse coarse coding","author":"Agarwal","year":"1996","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"CoRR"},{"article-title":"A deep look at experience replay","year":"2017","author":"Zhang","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.103"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561388"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506078"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2890849"},{"key":"ref23","article-title":"Prioritized experience replay","author":"Schaul","year":"2016","journal-title":"CoRR"},{"key":"ref24","first-page":"01","article-title":"The epsilon greedy algorithm - a performance review","volume":"6","author":"Agarwal","year":"2020","journal-title":"International Journal of New Technology and Research"},{"key":"ref25","first-page":"1038","article-title":"Time limits in reinforcement learning","volume-title":"In International Conference on Machine Learning","author":"Pardo"}],"event":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2022,10,16]]},"location":"Bordeaux, France","end":{"date-parts":[[2022,10,19]]}},"container-title":["2022 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9897158\/9897159\/09897349.pdf?arnumber=9897349","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:00:24Z","timestamp":1705957224000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9897349\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,16]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icip46576.2022.9897349","relation":{},"subject":[],"published":{"date-parts":[[2022,10,16]]}}}