{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T04:04:31Z","timestamp":1750737871288,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":39,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819665846","type":"print"},{"value":"9789819665853","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-6585-3_13","type":"book-chapter","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T14:41:48Z","timestamp":1750689708000},"page":"182-196","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Data Augmentation for\u00a0Continual RL via\u00a0Adversarial Gradient Episodic Memory"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7032-8903","authenticated-orcid":false,"given":"Sihao","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3474-349X","authenticated-orcid":false,"given":"Xingyu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6267-0366","authenticated-orcid":false,"given":"Xiaowei","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,24]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Aljundi, R., Babiloni, F., Elhoseiny, M., Rohrbach, M., Tuytelaars, T.: Memory aware synapses: learning what (not) to forget. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 139\u2013154 (2018)","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"13_CR2","unstructured":"Chaudhry, A., Ranzato, M., Rohrbach, M., Elhoseiny, M.: Efficient lifelong learning with a-GEM. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=Hkf2_sC5FX"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Ciregan, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3642\u20133649. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248110"},{"key":"13_CR4","unstructured":"Cire\u015fan, D.C., Meier, U., Masci, J., Gambardella, L.M., Schmidhuber, J.: High-performance neural networks for visual object classification. arXiv preprint arXiv:1102.0183 (2011)"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Fang, M., Li, Y., Cohn, T.: Learning how to active learn: a deep reinforcement learning approach. arXiv preprint arXiv:1708.02383 (2017)","DOI":"10.18653\/v1\/D17-1063"},{"key":"13_CR6","unstructured":"Feng, S.Y., et al.: A survey of data augmentation approaches for NLP. arXiv preprint arXiv:2105.03075 (2021)"},{"key":"13_CR7","unstructured":"Guo, Y., Liu, M., Yang, T., Rosing, T.: Improved schemes for episodic memory-based lifelong learning. In: Advances in Neural Information Processing Systems, vol. 33, pp. 1023\u20131035 (2020)"},{"key":"13_CR8","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870. PMLR (2018)"},{"key":"13_CR9","unstructured":"Hansen, N., Su, H., Wang, X.: Stabilizing deep q-learning with convnets and vision transformers under data augmentation. In: Advances in Neural Information Processing Systems, vol. 34, pp. 3680\u20133693 (2021)"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Jin, G., Yi, X., Huang, W., Schewe, S., Huang, X.: Enhancing adversarial training with second-order statistics of weights. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15273\u201315283 (2022)","DOI":"10.1109\/CVPR52688.2022.01484"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Jindal, A., Chowdhury, A.G., Didolkar, A., Jin, D., Sawhney, R., Shah, R.: Augmenting NLP models using latent feature interpolations. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 6931\u20136936 (2020)","DOI":"10.18653\/v1\/2020.coling-main.611"},{"key":"13_CR12","unstructured":"Kirk, R., Zhang, A., Grefenstette, E., Rockt\u00e4schel, T.: A survey of generalisation in deep reinforcement learning. arXiv preprint arXiv:2111.09794 (2021)"},{"issue":"13","key":"13_CR13","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. 114(13), 3521\u20133526 (2017)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"13_CR14","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)"},{"key":"13_CR15","unstructured":"Laskin, M., Lee, K., Stooke, A., Pinto, L., Abbeel, P., Srinivas, A.: Reinforcement learning with augmented data. In: Advances in Neural Information Processing Systems, vol. 33, pp. 19884\u201319895 (2020)"},{"issue":"11","key":"13_CR16","doi-asserted-by":"publisher","first-page":"8196","DOI":"10.1109\/TPAMI.2021.3109287","volume":"44","author":"J Li","year":"2022","unstructured":"Li, J., Du, Z., Zhu, L., Ding, Z., Lu, K., Shen, H.T.: Divergence-agnostic unsupervised domain adaptation by adversarial attacks. IEEE Trans. Pattern Anal. Mach. Intell. 44(11), 8196\u20138211 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2021.3109287","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR17","unstructured":"Liang, K.J., et al.: Mixkd: towards efficient distillation of large-scale language models. In: International Conference on Learning Representations (2020)"},{"key":"13_CR18","unstructured":"Liu, J., et al.: Tiny refinements elicit resilience: toward efficient prefix-model against LLM red-teaming. arXiv preprint arXiv:2405.12604 (2024)"},{"key":"13_CR19","unstructured":"Lopez-Paz, D., Ranzato, M.: Gradient episodic memory for continual learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"13_CR20","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. In: International Conference on Learning Representations (2018)"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Mallya, A., Lazebnik, S.: Packnet: adding multiple tasks to a single network by iterative pruning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7765\u20137773 (2018)","DOI":"10.1109\/CVPR.2018.00810"},{"key":"13_CR22","unstructured":"Nguyen, C.V., Li, Y., Bui, T.D., Turner, R.E.: Variational continual learning. In: International Conference on Learning Representations (2018)"},{"key":"13_CR23","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. In: Advances in Neural Information Processing Systems, vol. 35, pp. 27730\u201327744 (2022)"},{"key":"13_CR24","unstructured":"Raileanu, R., Goldstein, M., Yarats, D., Kostrikov, I., Fergus, R.: Automatic data augmentation for generalization in deep reinforcement learning. arXiv preprint arXiv:2006.12862 (2020)"},{"key":"13_CR25","unstructured":"Saha, G., Garg, I., Roy, K.: Gradient projection memory for continual learning. In: International Conference on Learning Representations (2020)"},{"key":"13_CR26","unstructured":"Shalev-Shwartz, S., Shammah, S., Shashua, A.: Safe, multi-agent, reinforcement learning for autonomous driving. arXiv preprint arXiv:1610.03295 (2016)"},{"issue":"1","key":"13_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","volume":"6","author":"C Shorten","year":"2019","unstructured":"Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(1), 1\u201348 (2019)","journal-title":"J. Big Data"},{"issue":"2","key":"13_CR28","doi-asserted-by":"publisher","first-page":"945","DOI":"10.1007\/s10462-021-09997-9","volume":"55","author":"B Singh","year":"2022","unstructured":"Singh, B., Kumar, R., Singh, V.P.: Reinforcement learning in robotic applications: a comprehensive survey. Artif. Intell. Rev. 55(2), 945\u2013990 (2022)","journal-title":"Artif. Intell. Rev."},{"key":"13_CR29","unstructured":"Sinha, S., Mandlekar, A., Garg, A.: S4RL: surprisingly simple self-supervision for offline reinforcement learning in robotics. In: Conference on Robot Learning, pp. 907\u2013917. PMLR (2022)"},{"key":"13_CR30","unstructured":"Volpi, R., Namkoong, H., Sener, O., Duchi, J.C., Murino, V., Savarese, S.: Generalizing to unseen domains via adversarial data augmentation. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"13_CR31","unstructured":"Wang, K., Kang, B., Shao, J., Feng, J.: Improving generalization in reinforcement learning with mixture regularization. In: Advances in Neural Information Processing Systems, vol. 33, pp. 7968\u20137978 (2020)"},{"key":"13_CR32","unstructured":"Wang, Z., Shen, L., Fang, L., Suo, Q., Duan, T., Gao, M.: Improving task-free continual learning by distributionally robust memory evolution. In: Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G., Sabato, S. (eds.) Proceedings of the 39th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0162, pp. 22985\u201322998. PMLR (2022). https:\/\/proceedings.mlr.press\/v162\/wang22v.html"},{"key":"13_CR33","unstructured":"Wolczyk, M., Zajac, M., Pascanu, R., Kuci\u0144ski, \u0141., Mi\u0142o\u015b, P.: Continual world: a robotic benchmark for continual reinforcement learning. In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems (2021). https:\/\/openreview.net\/forum?id=5qsptDcsdEj"},{"key":"13_CR34","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 (2021). https:\/\/openreview.net\/forum?id=GY6-6sTvGaf"},{"key":"13_CR35","doi-asserted-by":"crossref","unstructured":"Yin, X., et al.: ReRoGCRL: representation-based robustness in goal-conditioned reinforcement learning. In: Proceedings of 38th Annual AAAI Conference on Artificial Intelligence (AAAI\u201924). Association for the Advancement of Artificial Intelligence (AAAI) (2023)","DOI":"10.1609\/aaai.v38i19.30176"},{"key":"13_CR36","unstructured":"Yu, T., et al.: Meta-world: a benchmark and evaluation for multi-task and meta reinforcement learning. In: Conference on Robot Learning, pp. 1094\u20131100. PMLR (2020)"},{"key":"13_CR37","unstructured":"Zhang, H., Guo, Y.: Generalization of reinforcement learning with policy-aware adversarial data augmentation. arXiv preprint arXiv:2106.15587 (2021)"},{"key":"13_CR38","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)"},{"key":"13_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, M., Naresh, N.U., He, Y.: Adversarial data augmentation for task-specific knowledge distillation of pre-trained transformers. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 11685\u201311693 (2022)","DOI":"10.1609\/aaai.v36i10.21423"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-6585-3_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T14:41:59Z","timestamp":1750689719000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-6585-3_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819665846","9789819665853"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-6585-3_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","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":"2 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}