{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,12]],"date-time":"2025-08-12T21:55:08Z","timestamp":1755035708439,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":49,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819609680"},{"type":"electronic","value":"9789819609697"}],"license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-0969-7_23","type":"book-chapter","created":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T12:53:47Z","timestamp":1733576027000},"page":"387-401","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Robust Visual Reinforcement Learning by\u00a0Prompt Tuning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0614-1746","authenticated-orcid":false,"given":"Tung","family":"Tran","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8615-2854","authenticated-orcid":false,"given":"Khoat","family":"Than","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7442-1279","authenticated-orcid":false,"given":"Danilo","family":"Vargas","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,8]]},"reference":[{"key":"23_CR1","unstructured":"Agarwal, R., Machado, M.C., Castro, P.S., Bellemare, M.G.: Contrastive behavioral similarity embeddings for generalization in reinforcement learning. arXiv preprint arXiv:2101.05265 (2021)"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Bellman, R.: A markovian decision process. Journal of mathematics and mechanics pp. 679\u2013684 (1957)","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"23_CR3","first-page":"9912","volume":"33","author":"M Caron","year":"2020","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. Adv. Neural. Inf. Process. Syst. 33, 9912\u20139924 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Chebotar, Y., Handa, A., Makoviychuk, V., Macklin, M., Issac, J., Ratliff, N., Fox, D.: Closing the sim-to-real loop: Adapting simulation randomization with real world experience. In: 2019 International Conference on Robotics and Automation (ICRA). pp. 8973\u20138979. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8793789"},{"key":"23_CR5","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International conference on machine learning. pp. 1597\u20131607. PMLR (2020)"},{"key":"23_CR6","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., Xie, S., He, K.: An empirical study of training self-supervised vision transformers. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 9640\u20139649 (2021)","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"23_CR8","unstructured":"Choi, W., Kim, W.K., Kim, S., Woo, H.: Efficient policy adaptation with contrastive prompt ensemble for embodied agents. In: Thirty-seventh Conference on Neural Information Processing Systems (2023), https:\/\/openreview.net\/forum?id=Ny3GcHLyzj"},{"key":"23_CR9","unstructured":"Cobbe, K., Klimov, O., Hesse, C., Kim, T., Schulman, J.: Quantifying generalization in reinforcement learning. In: International conference on machine learning. pp. 1282\u20131289. PMLR (2019)"},{"key":"23_CR10","unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International conference on machine learning. pp. 1587\u20131596. PMLR (2018)"},{"key":"23_CR11","unstructured":"Gelada, C., Kumar, S., Buckman, J., Nachum, O., Bellemare, M.G.: Deepmdp: Learning continuous latent space models for representation learning. In: International conference on machine learning. pp. 2170\u20132179. PMLR (2019)"},{"key":"23_CR12","first-page":"3680","volume":"34","author":"N Hansen","year":"2021","unstructured":"Hansen, N., Su, H., Wang, X.: Stabilizing deep q-learning with convnets and vision transformers under data augmentation. Adv. Neural. Inf. Process. Syst. 34, 3680\u20133693 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Hansen, N., Wang, X.: Generalization in reinforcement learning by soft data augmentation. In: 2021 IEEE International Conference on Robotics and Automation (ICRA). pp. 13611\u201313617. IEEE (2021)","DOI":"10.1109\/ICRA48506.2021.9561103"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"23_CR17","unstructured":"Jaderberg, M., Mnih, V., Czarnecki, W.M., Schaul, T., Leibo, J.Z., Silver, D., Kavukcuoglu, K.: Reinforcement learning with unsupervised auxiliary tasks. arXiv preprint arXiv:1611.05397 (2016)"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Jia, M., Tang, L., Chen, B.C., Cardie, C., Belongie, S., Hariharan, B., Lim, S.N.: Visual prompt tuning. In: European Conference on Computer Vision. pp. 709\u2013727. Springer (2022)","DOI":"10.1007\/978-3-031-19827-4_41"},{"issue":"1\u20132","key":"23_CR19","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/S0004-3702(98)00023-X","volume":"101","author":"LP Kaelbling","year":"1998","unstructured":"Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and acting in partially observable stochastic domains. Artif. Intell. 101(1\u20132), 99\u2013134 (1998)","journal-title":"Artif. Intell."},{"key":"23_CR20","unstructured":"Kalashnikov, D., Irpan, A., Pastor, P., Ibarz, J., Herzog, A., Jang, E., Quillen, D., Holly, E., Kalakrishnan, M., Vanhoucke, V., et\u00a0al.: Scalable deep reinforcement learning for vision-based robotic manipulation. In: Conference on robot learning. pp. 651\u2013673. PMLR (2018)"},{"key":"23_CR21","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"23_CR22","unstructured":"Laskin, M., Srinivas, A., Abbeel, P.: Curl: Contrastive unsupervised representations for reinforcement learning. In: International conference on machine learning. pp. 5639\u20135650. PMLR (2020)"},{"issue":"39","key":"23_CR23","first-page":"1","volume":"17","author":"S Levine","year":"2016","unstructured":"Levine, S., Finn, C., Darrell, T., Abbeel, P.: End-to-end training of deep visuomotor policies. J. Mach. Learn. Res. 17(39), 1\u201340 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"23_CR24","unstructured":"Lillicrap, T.P., Hunt, J.J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., Wierstra, D.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"23_CR25","unstructured":"Lin, X., Baweja, H., Kantor, G., Held, D.: Adaptive auxiliary task weighting for reinforcement learning. Advances in neural information processing systems 32 (2019)"},{"issue":"9","key":"23_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3560815","volume":"55","author":"P Liu","year":"2023","unstructured":"Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., Neubig, G.: Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. ACM Comput. Surv. 55(9), 1\u201335 (2023)","journal-title":"ACM Comput. Surv."},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Liu, X., Ji, K., Fu, Y., Tam, W.L., Du, Z., Yang, Z., Tang, J.: P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks. arXiv preprint arXiv:2110.07602 (2021)","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"23_CR28","unstructured":"Lyle, C., Rowland, M., Ostrovski, G., Dabney, W.: On the effect of auxiliary tasks on representation dynamics. In: International Conference on Artificial Intelligence and Statistics. pp.\u00a01\u20139. PMLR (2021)"},{"key":"23_CR29","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., et\u00a0al.: Human-level control through deep reinforcement learning. nature 518(7540), 529\u2013533 (2015)","DOI":"10.1038\/nature14236"},{"key":"23_CR31","unstructured":"Parisi, S., Rajeswaran, A., Purushwalkam, S., Gupta, A.: The unsurprising effectiveness of pre-trained vision models for control. In: international conference on machine learning. pp. 17359\u201317371. PMLR (2022)"},{"key":"23_CR32","doi-asserted-by":"publisher","unstructured":"Peng, X.B., Andrychowicz, M., Zaremba, W., Abbeel, P.: Sim-to-real transfer of robotic control with dynamics randomization. In: 2018 IEEE International Conference on Robotics and Automation (ICRA). IEEE (May 2018). https:\/\/doi.org\/10.1109\/icra.2018.8460528, http:\/\/dx.doi.org\/10.1109\/ICRA.2018.8460528","DOI":"10.1109\/icra.2018.8460528"},{"key":"23_CR33","doi-asserted-by":"crossref","unstructured":"Pinto, L., Andrychowicz, M., Welinder, P., Zaremba, W., Abbeel, P.: Asymmetric actor critic for image-based robot learning (2017)","DOI":"10.15607\/RSS.2018.XIV.008"},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Ramos, F., Possas, R.C., Fox, D.: Bayessim: adaptive domain randomization via probabilistic inference for robotics simulators. arXiv preprint arXiv:1906.01728 (2019)","DOI":"10.15607\/RSS.2019.XV.029"},{"key":"23_CR35","unstructured":"Schwarzer, M., Anand, A., Goel, R., Hjelm, R.D., Courville, A., Bachman, P.: Data-efficient reinforcement learning with self-predictive representations. arXiv preprint arXiv:2007.05929 (2020)"},{"key":"23_CR36","unstructured":"Sekar, R., Rybkin, O., Daniilidis, K., Abbeel, P., Hafner, D., Pathak, D.: Planning to explore via self-supervised world models. In: International conference on machine learning. pp. 8583\u20138592. PMLR (2020)"},{"key":"23_CR37","unstructured":"Shah, R., Kumar, V.: Rrl: Resnet as representation for reinforcement learning. arXiv preprint arXiv:2107.03380 (2021)"},{"key":"23_CR38","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: An introduction. MIT press (2018)"},{"key":"23_CR39","unstructured":"Tassa, Y., Doron, Y., Muldal, A., Erez, T., Li, Y., Casas, D.d.L., Budden, D., Abdolmaleki, A., Merel, J., Lefrancq, A., et\u00a0al.: Deepmind control suite. arXiv preprint arXiv:1801.00690 (2018)"},{"key":"23_CR40","doi-asserted-by":"crossref","unstructured":"Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., Abbeel, P.: Domain randomization for transferring deep neural networks from simulation to the real world. In: 2017 IEEE\/RSJ international conference on intelligent robots and systems (IROS). pp. 23\u201330. IEEE (2017)","DOI":"10.1109\/IROS.2017.8202133"},{"key":"23_CR41","unstructured":"Yarats, D., Fergus, R., Lazaric, A., Pinto, L.: Mastering visual continuous control: Improved data-augmented reinforcement learning. arXiv preprint arXiv:2107.09645 (2021)"},{"key":"23_CR42","unstructured":"Yarats, D., Fergus, R., Lazaric, A., Pinto, L.: Reinforcement learning with prototypical representations. In: International Conference on Machine Learning. pp. 11920\u201311931. PMLR (2021)"},{"key":"23_CR43","unstructured":"Yarats, D., Kostrikov, I., Fergus, R.: Image augmentation is all you need: Regularizing deep reinforcement learning from pixels. In: International conference on learning representations (2020)"},{"key":"23_CR44","doi-asserted-by":"crossref","unstructured":"Yarats, D., Zhang, A., Kostrikov, I., Amos, B., Pineau, J., Fergus, R.: Improving sample efficiency in model-free reinforcement learning from images. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a035, pp. 10674\u201310681 (2021)","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"23_CR45","doi-asserted-by":"crossref","unstructured":"Yuan, Z., Ma, G., Mu, Y., Xia, B., Yuan, B., Wang, X., Luo, P., Xu, H.: Don\u2019t touch what matters: Task-aware lipschitz data augmentation for visual reinforcement learning. arXiv preprint arXiv:2202.09982 (2022)","DOI":"10.24963\/ijcai.2022\/514"},{"key":"23_CR46","first-page":"13022","volume":"35","author":"Z Yuan","year":"2022","unstructured":"Yuan, Z., Xue, Z., Yuan, B., Wang, X., Wu, Y., Gao, Y., Xu, H.: Pre-trained image encoder for generalizable visual reinforcement learning. Adv. Neural. Inf. Process. Syst. 35, 13022\u201313037 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR47","unstructured":"Zhang, A., McAllister, R., Calandra, R., Gal, Y., Levine, S.: Learning invariant representations for reinforcement learning without reconstruction. arXiv preprint arXiv:2006.10742 (2020)"},{"key":"23_CR48","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Mottaghi, R., Kolve, E., Lim, J.J., Gupta, A., Fei-Fei, L., Farhadi, A.: Target-driven visual navigation in indoor scenes using deep reinforcement learning. In: 2017 IEEE international conference on robotics and automation (ICRA). pp. 3357\u20133364. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989381"},{"issue":"1","key":"23_CR49","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","volume":"109","author":"F Zhuang","year":"2020","unstructured":"Zhuang, F., Qi, Z., Duan, K., Xi, D., Zhu, Y., Zhu, H., Xiong, H., He, Q.: A comprehensive survey on transfer learning. Proc. IEEE 109(1), 43\u201376 (2020)","journal-title":"Proc. IEEE"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0969-7_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T13:06:37Z","timestamp":1733576797000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0969-7_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"ISBN":["9789819609680","9789819609697"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0969-7_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,8]]},"assertion":[{"value":"8 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}