{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T00:44:06Z","timestamp":1760489046076,"version":"build-2065373602"},"reference-count":55,"publisher":"Association for Computing Machinery (ACM)","issue":"10","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2025,10,31]]},"abstract":"<jats:p>\n            Visual reinforcement learning has exhibited efficacy in solving control tasks characterized by high-dimensional observations. However, a central challenge persists in deriving dependable and generalizable representations from vision-based observations. Inspired by the human thought process, when the visual representation extracted from the observation can predict the future and trace history, the representation is reliable and accurate in comprehending the environmental state. Based on this concept, we introduce a\n            <jats:italic toggle=\"yes\">B<\/jats:italic>\n            idirectional\n            <jats:italic toggle=\"yes\">T<\/jats:italic>\n            ransition (BT) framework for representation learning. This framework employs the bidirectional prediction of both forward and backward environmental transitions as auxiliary tasks to extract reliable representations. Additionally, we introduce an inverse dynamic model to predict the actions causing environmental state transitions, thereby learning the task relevance of state representations. Our method demonstrates competitive generalization performance and sample efficiency in two settings in the DeepMind Control suite. Moreover, we utilize the robotic manipulation simulator, autonomous driving simulator CARLA, and visual navigation simulator Habitat to demonstrate the wide applicability of our method. The results indicate that BT offers more stable and reliable representations and exhibits robust generalization performance for visual reinforcement learning tasks.\n          <\/jats:p>","DOI":"10.1145\/3765517","type":"journal-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T15:23:01Z","timestamp":1756826581000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning Robust Representations via Bidirectional Transition for Visual Reinforcement Learning"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6541-2784","authenticated-orcid":false,"given":"Xiaobo","family":"Hu","sequence":"first","affiliation":[{"name":"Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1611-4323","authenticated-orcid":false,"given":"Youfang","family":"Lin","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6280-0801","authenticated-orcid":false,"given":"Jinwen","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0639-0994","authenticated-orcid":false,"given":"Yue","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6599-3638","authenticated-orcid":false,"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9572-2345","authenticated-orcid":false,"given":"Hehe","family":"Fan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6533-5176","authenticated-orcid":false,"given":"Kai","family":"Lv","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,14]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_1_2_2","DOI":"10.1016\/j.eswa.2024.124951"},{"doi-asserted-by":"publisher","key":"e_1_3_1_3_2","DOI":"10.3390\/en16031512"},{"unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Alex Graves Ioannis Antonoglou Daan Wierstra and Martin Riedmiller. 2013. Playing Atari with deep reinforcement learning. arXiv:1312.5602. Retrieved from https:\/\/arxiv.org\/abs\/1312.5602","key":"e_1_3_1_4_2"},{"doi-asserted-by":"publisher","key":"e_1_3_1_5_2","DOI":"10.5555\/2946645.2946684"},{"key":"e_1_3_1_6_2","first-page":"1","article-title":"Building category graphs representation with spatial and temporal attention for visual navigation","author":"Hu Xiaobo","year":"2024","unstructured":"Xiaobo Hu, Youfang Lin, HeHe Fan, Shuo Wang, Zhihao Wu, and Kai Lv. 2024. Building category graphs representation with spatial and temporal attention for visual navigation. ACM Transactions on Multimedia Computing, Communications and Applications 20, 7 (2024), 1\u201322.","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications"},{"doi-asserted-by":"publisher","key":"e_1_3_1_7_2","DOI":"10.1109\/TMM.2023.3243618"},{"doi-asserted-by":"publisher","key":"e_1_3_1_8_2","DOI":"10.1109\/TCSVT.2023.3291131"},{"issue":"1","key":"e_1_3_1_9_2","first-page":"25","article-title":"Category-stitch learning for union domain generalization","volume":"19","author":"Liu Yajing","year":"2023","unstructured":"Yajing Liu, Zhiwei Xiong, Ya Li, Yuning Lu, Xinmei Tian, and Zheng-Jun Zha. 2023. Category-stitch learning for union domain generalization. ACM Transactions on Multimedia Computing, Communications, and Applications 19, 1 (2023), 25:21\u201325:19.","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications"},{"issue":"6","key":"e_1_3_1_10_2","first-page":"184:1","article-title":"MultiMatch: Multi-task learning for semi-supervised domain generalization","volume":"20","author":"Qi Lei","year":"2024","unstructured":"Lei Qi, Hongpeng Yang, Yinghuan Shi, and Xin Geng. 2024. MultiMatch: Multi-task learning for semi-supervised domain generalization. ACM Transactions on Multimedia Computing, Communications, and Applications 20, 6 (2024), 184:1\u2013184:21.","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications"},{"issue":"6","key":"e_1_3_1_11_2","first-page":"157:1","article-title":"Vocoder detection of spoofing speech based on GAN fingerprints and domain generalization","volume":"20","author":"Li Fan","year":"2024","unstructured":"Fan Li, Yanxiang Chen, Haiyang Liu, Zuxing Zhao, Yuanzhi Yao, and Xin Liao. 2024. Vocoder detection of spoofing speech based on GAN fingerprints and domain generalization. ACM Transactions on Multimedia Computing, Communications, and Applications 20, 6 (2024), 157:1\u2013157:20.","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications"},{"doi-asserted-by":"publisher","key":"e_1_3_1_12_2","DOI":"10.1145\/3624015"},{"key":"e_1_3_1_13_2","first-page":"1282","volume-title":"International Conference on Machine Learning. PMLR","author":"Cobbe Karl","year":"2019","unstructured":"Karl Cobbe, Oleg Klimov, Chris Hesse, Taehoon Kim, and John Schulman. 2019. Quantifying generalization in reinforcement learning. In International Conference on Machine Learning. PMLR, 1282\u20131289."},{"unstructured":"Chiyuan Zhang Oriol Vinyals Remi Munos and Samy Bengio. 2018. A study on overfitting in deep reinforcement learning. arXiv:1804.06893. Retrieved from https:\/\/arxiv.org\/abs\/1804.06893","key":"e_1_3_1_14_2"},{"key":"e_1_3_1_15_2","first-page":"21271","article-title":"Bootstrap your own latent\u2014A new approach to self-supervised learning","volume":"33","author":"Grill Jean-Bastien","year":"2020","unstructured":"Jean-Bastien Grill, Florian Strub, Florent Altch\u00e9, Corentin Tallec, Pierre Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires, Zhaohan Guo, Mohammad Gheshlaghi Azar, et al. 2020. Bootstrap your own latent\u2014A new approach to self-supervised learning. In Advances in Neural Information Processing Systems, Vol. 33, 21271\u201321284.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_16_2","first-page":"5639","volume-title":"International Conference on Machine Learning","author":"Laskin Michael","year":"2020","unstructured":"Michael Laskin, Aravind Srinivas, and Pieter Abbeel. 2020. Curl: Contrastive unsupervised representations for reinforcement learning. In International Conference on Machine Learning. PMLR, 5639\u20135650."},{"key":"e_1_3_1_17_2","first-page":"5590","volume-title":"38th AAAI Conference on Artificial Intelligence (AAAI \u201924)","author":"Wang Shuo","year":"2024","unstructured":"Shuo Wang, Zhihao Wu, Xiaobo Hu, Jinwen Wang, Youfang Lin, and Kai Lv. 2024. What effects the generalization in visual reinforcement learning: Policy consistency with truncated return prediction. In 38th AAAI Conference on Artificial Intelligence (AAAI \u201924). AAAI Press, 5590\u20135598."},{"doi-asserted-by":"publisher","key":"e_1_3_1_18_2","DOI":"10.1109\/ICRA48506.2021.9561103"},{"key":"e_1_3_1_19_2","first-page":"29420","article-title":"Offline reinforcement learning with reverse model-based imagination","volume":"34","author":"Wang Jianhao","year":"2021","unstructured":"Jianhao Wang, Wenzhe Li, Haozhe Jiang, Guangxiang Zhu, Siyuan Li, and Chongjie Zhang. 2021. Offline reinforcement learning with reverse model-based imagination. In Advances in Neural Information Processing Systems, Vol. 34, 29420\u201329432.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_20_2","first-page":"5618","volume-title":"International Conference on Machine Learning","author":"Lai Hang","year":"2020","unstructured":"Hang Lai, Jian Shen, Weinan Zhang, and Yong Yu. 2020. Bidirectional model-based policy optimization. In International Conference on Machine Learning. PMLR, 5618\u20135627."},{"key":"e_1_3_1_21_2","first-page":"38218","article-title":"Double check your state before trusting it: Confidence-aware bidirectional offline model-based imagination","volume":"35","author":"Lyu Jiafei","year":"2022","unstructured":"Jiafei Lyu, Xiu Li, and Zongqing Lu. 2022. Double check your state before trusting it: Confidence-aware bidirectional offline model-based imagination. In Advances in Neural Information Processing Systems, Vol. 35, 38218\u201338231.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_22_2","first-page":"29454","article-title":"Bidirectional learning for offline infinite-width model-based optimization","volume":"35","author":"Chen Can","year":"2022","unstructured":"Can Chen, Yingxueff Zhang, Jie Fu, Xue Steve Liu, and Mark Coates. 2022. Bidirectional learning for offline infinite-width model-based optimization. In Advances in Neural Information Processing Systems, Vol. 35, 29454\u201329467.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_23_2","first-page":"3150","volume-title":"IJCAI International Joint Conference on Artificial Intelligence","author":"Kim Kyungsoo","year":"2022","unstructured":"Kyungsoo Kim, Jeongsoo Ha, and Yusung Kim. 2022. Self-predictive dynamics for generalization of vision-based reinforcement learning. In IJCAI International Joint Conference on Artificial Intelligence. International Joint Conferences on Artificial Intelligence, 3150\u20133156."},{"key":"e_1_3_1_24_2","volume-title":"9th International Conference on Learning Representations","author":"Schwarzer Max","year":"2021","unstructured":"Max Schwarzer, Ankesh Anand, Rishab Goel, R. Devon Hjelm, Aaron C. Courville, and Philip Bachman. 2021. Data-efficient reinforcement learning with self-predictive representations. In 9th International Conference on Learning Representations."},{"key":"e_1_3_1_25_2","volume-title":"9th International Conference on Learning Representations (ICLR \u201921)","author":"Hansen Nicklas","year":"2021","unstructured":"Nicklas Hansen, Rishabh Jangir, Yu Sun, Guillem Aleny\u00e0, Pieter Abbeel, Alexei A. Efros, Lerrel Pinto, and Xiaolong Wang. 2021. Self-supervised policy adaptation during deployment. In 9th International Conference on Learning Representations (ICLR \u201921). OpenReview.net."},{"doi-asserted-by":"publisher","key":"e_1_3_1_26_2","DOI":"10.1038\/381425a0"},{"doi-asserted-by":"publisher","key":"e_1_3_1_27_2","DOI":"10.1037\/h0061626"},{"key":"e_1_3_1_28_2","first-page":"2170","volume-title":"International Conference on Machine Learning","author":"Gelada Carles","year":"2019","unstructured":"Carles Gelada, Saurabh Kumar, Jacob Buckman, Ofir Nachum, and Marc G. Bellemare. 2019. Deepmdp: Learning continuous latent space models for representation learning. In International Conference on Machine Learning. PMLR, 2170\u20132179."},{"key":"e_1_3_1_29_2","first-page":"33632","volume-title":"International Conference on Machine Learning","author":"Tang Yunhao","year":"2023","unstructured":"Yunhao Tang, Zhaohan Daniel Guo, Pierre Harvey Richemond, Bernardo Avila Pires, Yash Chandak, R\u00e9mi Munos, Mark Rowland, Mohammad Gheshlaghi Azar, Charline Le Lan, Clare Lyle, et al. 2023. Understanding self-predictive learning for reinforcement learning. In International Conference on Machine Learning. PMLR, 33632\u201333656."},{"key":"e_1_3_1_30_2","first-page":"1861","volume-title":"International Conference on Machine Learning","author":"Haarnoja Tuomas","year":"2018","unstructured":"Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, and Sergey Levine. 2018. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In International Conference on Machine Learning. PMLR, 1861\u20131870."},{"unstructured":"Yuval Tassa Yotam Doron Alistair Muldal Tom Erez Yazhe Li Diego de Las Casas David Budden Abbas Abdolmaleki Josh Merel Andrew Lefrancq et al. 2018. Deepmind control suite. arXiv:1801.00690. Retrieved from https:\/\/arxiv.org\/abs\/1801.00690","key":"e_1_3_1_31_2"},{"issue":"2","key":"e_1_3_1_32_2","doi-asserted-by":"crossref","first-page":"3046","DOI":"10.1109\/LRA.2022.3144512","article-title":"Look closer: Bridging egocentric and third-person views with transformers for robotic manipulation","volume":"7","author":"Jangir Rishabh","year":"2022","unstructured":"Rishabh Jangir, Nicklas Hansen, Sambaran Ghosal, Mohit Jain, and Xiaolong Wang. 2022. Look closer: Bridging egocentric and third-person views with transformers for robotic manipulation. IEEE Robotics and Automation Letters 7, 2 (2022), 3046\u20133053.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"e_1_3_1_33_2","first-page":"1","volume-title":"Conference on Robot Learning","author":"Dosovitskiy Alexey","year":"2017","unstructured":"Alexey Dosovitskiy, German Ros, Felipe Codevilla, Antonio Lopez, and Vladlen Koltun. 2017. CARLA: An open urban driving simulator. In Conference on Robot Learning. PMLR, 1\u201316."},{"unstructured":"Santhosh K. Ramakrishnan Aaron Gokaslan Erik Wijmans Oleksandr Maksymets Alex Clegg John Turner Eric Undersander Wojciech Galuba Andrew Westbury Angel X. Chang et al. 2021. Habitat-matterport 3d dataset (hm3d): 1000 large-scale 3d environments for embodied AI. arXiv:2109.08238. Retrieved from https:\/\/arxiv.org\/abs\/2109.08238","key":"e_1_3_1_34_2"},{"key":"e_1_3_1_35_2","volume-title":"8th International Conference on Learning Representations (ICLR \u201920","author":"Lee Kimin","year":"2020","unstructured":"Kimin Lee, Kibok Lee, Jinwoo Shin, and Honglak Lee. 2020. Network randomization: A simple technique for generalization in deep reinforcement learning. In 8th International Conference on Learning Representations (ICLR \u201920). OpenReview.net."},{"key":"e_1_3_1_36_2","first-page":"19884","article-title":"Pieter Abbeel, and Aravind Srinivas","volume":"33","author":"Laskin Misha","year":"2020","unstructured":"Misha Laskin, Kimin Lee, Adam Stooke, Lerrel Pinto, Pieter Abbeel, and Aravind Srinivas. 2020. Reinforcement learning with augmented data. In Advances in Neural Information Processing Systems, Vol. 33, 19884\u201319895.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_37_2","volume-title":"International Conference on Learning Representations","author":"Yarats Denis","year":"2020","unstructured":"Denis Yarats, Ilya Kostrikov, and Rob Fergus. 2020. Image augmentation is all you need: Regularizing deep reinforcement learning from pixels. In International Conference on Learning Representations."},{"key":"e_1_3_1_38_2","first-page":"5402","article-title":"Automatic data augmentation for generalization in reinforcement learning","volume":"34","author":"Raileanu Roberta","year":"2021","unstructured":"Roberta Raileanu, Maxwell Goldstein, Denis Yarats, Ilya Kostrikov, and Rob Fergus. 2021. Automatic data augmentation for generalization in reinforcement learning. In Advances in Neural Information Processing Systems, Vol. 34, 5402\u20135415.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_39_2","first-page":"397","article-title":"Using confidence bounds for exploitation-exploration trade-offs","volume":"3","author":"Auer Peter","year":"2002","unstructured":"Peter Auer. 2002. Using confidence bounds for exploitation-exploration trade-offs. Journal of Machine Learning Research 3 (Nov. 2002), 397\u2013422.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_1_40_2","volume-title":"the 10th International Conference on Learning Representations (ICLR \u201922)","author":"Bertoin David","year":"2022","unstructured":"David Bertoin and Emmanuel Rachelson. 2022. Local feature swapping for generalization in reinforcement learning. In the 10th International Conference on Learning Representations (ICLR \u201922). OpenReview.net."},{"unstructured":"Guozheng Ma Zhen Wang Zhecheng Yuan Xueqian Wang Bo Yuan and Dacheng Tao. 2022. A comprehensive survey of data augmentation in visual reinforcement learning. arXiv:2210.04561. Retrieved from https:\/\/arxiv.org\/abs\/2210.04561","key":"e_1_3_1_41_2"},{"key":"e_1_3_1_42_2","first-page":"1597","volume-title":"International Conference on Machine Learning","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International Conference on Machine Learning. PMLR, 1597\u20131607."},{"key":"e_1_3_1_43_2","article-title":"Stabilizing deep q-learning with convnets and vision transformers under data augmentation","author":"Hansen Nicklas","year":"2021","unstructured":"Nicklas Hansen, Hao Su, and Xiaolong Wang. 2021. Stabilizing deep q-learning with convnets and vision transformers under data augmentation. In Advances in Neural Information Processing Systems, Vol. 34.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_44_2","first-page":"3702","volume-title":"31st International Joint Conference on Artificial Intelligence","author":"Yuan Zhecheng","year":"2022","unstructured":"Zhecheng Yuan, Guozheng Ma, Yao Mu, Bo Xia, Bo Yuan, Xueqian Wang, Ping Luo, and Huazhe Xu. 2022. Don\u2019t touch what matters: Task-aware Lipschitz data augmentation for visual reinforcement learning. In 31st International Joint Conference on Artificial Intelligence. ijcai.org, 3702\u20133708."},{"unstructured":"Amy Zhang Rowan McAllister Roberto Calandra Yarin Gal and Sergey Levine. 2020. Learning invariant representations for reinforcement learning without reconstruction. arXiv:2006.10742. Retrieved from https:\/\/arxiv.org\/abs\/2006.10742","key":"e_1_3_1_45_2"},{"doi-asserted-by":"publisher","key":"e_1_3_1_46_2","DOI":"10.1137\/10080484X"},{"key":"e_1_3_1_47_2","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton Richard S.","year":"2018","unstructured":"Richard S. Sutton and Andrew G. Barto. 2018. Reinforcement Learning: An Introduction. MIT Press."},{"key":"e_1_3_1_48_2","first-page":"2786","volume-title":"IEEE International Conference on Robotics and Automation (ICRA)","author":"Finn Chelsea","year":"2017","unstructured":"Chelsea Finn and Sergey Levine. 2017. Deep visual foresight for planning robot motion. In IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2786\u20132793."},{"key":"e_1_3_1_49_2","first-page":"19759","volume-title":"Advances in Neural Information Processing Systems","author":"Park Jung Yeon","year":"2022","unstructured":"Jung Yeon Park and Lawson Wong. 2022. Robust imitation of a few demonstrations with a backwards model. In Advances in Neural Information Processing Systems. S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35, Curran Associates, Inc., 19759\u201319772."},{"doi-asserted-by":"publisher","key":"e_1_3_1_50_2","DOI":"10.1016\/S0004-3702(98)00023-X"},{"doi-asserted-by":"publisher","key":"e_1_3_1_51_2","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"e_1_3_1_52_2","first-page":"11784","volume-title":"International Conference on Machine Learning","author":"Yang Mengjiao","year":"2021","unstructured":"Mengjiao Yang and Ofir Nachum. 2021. Representation matters: Offline pretraining for sequential decision making. In International Conference on Machine Learning. PMLR, 11784\u201311794."},{"key":"e_1_3_1_53_2","first-page":"11","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten Laurens","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research 9 (2008), 11.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_1_54_2","first-page":"30693","article-title":"Look where you look! Saliency-guided Q-networks for generalization in visual reinforcement learning","volume":"35","author":"Bertoin David","year":"2022","unstructured":"David Bertoin, Adil Zouitine, Mehdi Zouitine, and Emmanuel Rachelson. 2022. Look where you look! Saliency-guided Q-networks for generalization in visual reinforcement learning. In Advances in Neural Information Processing Systems, Vol. 35, 30693\u201330706.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_55_2","first-page":"6720","article-title":"RL-ViGen: A reinforcement learning benchmark for visual generalization","volume":"36","author":"Yuan Zhecheng","year":"2023","unstructured":"Zhecheng Yuan, Sizhe Yang, Pu Hua, Can Chang, Kaizhe Hu, and Huazhe Xu. 2023. RL-ViGen: A reinforcement learning benchmark for visual generalization. In Advances in Neural Information Processing Systems, Vol. 36, 6720\u20136747.","journal-title":"Advances in Neural Information Processing Systems"},{"unstructured":"Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980. Retrieved from https:\/\/arxiv.org\/abs\/1412.6980","key":"e_1_3_1_56_2"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3765517","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T21:23:06Z","timestamp":1760476986000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3765517"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,14]]},"references-count":55,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10,31]]}},"alternative-id":["10.1145\/3765517"],"URL":"https:\/\/doi.org\/10.1145\/3765517","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"type":"print","value":"1551-6857"},{"type":"electronic","value":"1551-6865"}],"subject":[],"published":{"date-parts":[[2025,10,14]]},"assertion":[{"value":"2024-06-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-10","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}