{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T21:36:18Z","timestamp":1767994578040,"version":"3.49.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032061058","type":"print"},{"value":"9783032061065","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-06106-5_9","type":"book-chapter","created":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T10:09:02Z","timestamp":1759399742000},"page":"146-162","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Continual Visual Reinforcement Learning with\u00a0A Life-Long World Model"],"prefix":"10.1007","author":[{"given":"Minting","family":"Pan","sequence":"first","affiliation":[]},{"given":"Wendong","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Geng","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Xiangming","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Siyu","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Yunbo","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,3]]},"reference":[{"key":"9_CR1","unstructured":"Ammar, H.B., Eaton, E., Ruvolo, P., Taylor, M.: Online multi-task learning for policy gradient methods. In: International Conference on Machine Learning, pp. 1206\u20131214 (2014)"},{"key":"9_CR2","unstructured":"Bharadhwaj, H., Babaeizadeh, M., Erhan, D., Levine, S.: Information prioritization through empowerment in visual model-based RL. In: International Conference on Learning Representations (2022)"},{"key":"9_CR3","unstructured":"Burchi, M., Timofte, R.: Learning transformer-based world models with contrastive predictive coding. In: International Conference on Learning Representations (2025)"},{"key":"9_CR4","unstructured":"Chen, G., et al.: Continual predictive learning from videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"9_CR5","unstructured":"Daniels, Z.A., et\u00a0al.: Model-free generative replay for lifelong reinforcement learning: Application to starcraft-2. In: Conference on Lifelong Learning Agents, pp. 1120\u20131145 (2022)"},{"key":"9_CR6","unstructured":"Dilokthanakul, N., et al.: Deep unsupervised clustering with gaussian mixture variational autoencoders. arXiv preprint arXiv:1611.02648 (2016)"},{"key":"9_CR7","unstructured":"Ha, D., Schmidhuber, J.: Recurrent world models facilitate policy evolution. In: Advances in neural information processing syste, vol.\u00a031 (2018)"},{"key":"9_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"},{"issue":"12","key":"9_CR9","doi-asserted-by":"publisher","first-page":"1028","DOI":"10.1016\/j.tics.2020.09.004","volume":"24","author":"R Hadsell","year":"2020","unstructured":"Hadsell, R., Rao, D., Rusu, A.A., Pascanu, R.: Embracing change: continual learning in deep neural networks. Trends Cogn. Sci. 24(12), 1028\u20131040 (2020)","journal-title":"Trends Cogn. Sci."},{"key":"9_CR10","unstructured":"Hafner, D., Lillicrap, T., Ba, J., Norouzi, M.: Dream to control: learning behaviors by latent imagination. In: International Conference on Learning Representations (2020)"},{"key":"9_CR11","unstructured":"Hafner, D., et al.: Learning latent dynamics for planning from pixels. In: International Conference on Machine Learning, pp. 2555\u20132565 (2019)"},{"key":"9_CR12","unstructured":"Hafner, D., Lillicrap, T.P., Norouzi, M., Ba, J.: Mastering atari with discrete world models. In: International Conference on Learning Representations (2021)"},{"key":"9_CR13","unstructured":"Hafner, D., et al.: Learning latent dynamics for planning from pixels. In: International Conference on Machine Learning, pp. 2555\u20132565 (2019)"},{"key":"9_CR14","unstructured":"Hansen, N., Lin, Y., Su, H., Wang, X., Kumar, V., Rajeswaran, A.: Modem: accelerating visual model-based reinforcement learning with demonstrations. arXiv preprint arXiv:2212.05698 (2022)"},{"key":"9_CR15","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"9_CR16","unstructured":"Igl, M., Farquhar, G., Luketina, J., B\u00f6hmer, J., Whiteson, S.: Transient non-stationarity and generalisation in deep reinforcement learning. In: International Conference on Learning Representations (2021)"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Zheng, Y., Tan, H., Tang, B., Zhou, H.: Variational deep embedding: an unsupervised and generative approach to clustering (2017)","DOI":"10.24963\/ijcai.2017\/273"},{"key":"9_CR18","doi-asserted-by":"publisher","first-page":"1401","DOI":"10.1613\/jair.1.13673","volume":"75","author":"K Khetarpal","year":"2022","unstructured":"Khetarpal, K., Riemer, M., Rish, I., Precup, D.: Towards continual reinforcement learning: a review and perspectives. J. Artif. Intell. Res. 75, 1401\u20131476 (2022)","journal-title":"J. Artif. Intell. Res."},{"issue":"13","key":"9_CR19","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick, J.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. 114(13), 3521\u20133526 (2017)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"9_CR20","unstructured":"Kostrikov, I., Yarats, D., Fergus, R.: Image augmentation is all you need: regularizing deep reinforcement learning from pixels. arXiv preprint arXiv:2004.13649 (2020)"},{"key":"9_CR21","unstructured":"Kumar, A., Zhou, A., Tucker, G., Levine, S.: Conservative q-learning for offline reinforcement learning. In: Advances in neural information processing system (2020)"},{"key":"9_CR22","unstructured":"Lan, Q., Pan, Y., Luo, J., Mahmood, A.R.: Memory-efficient reinforcement learning with knowledge consolidation. arXiv preprint arXiv:2205.10868 (2022)"},{"key":"9_CR23","unstructured":"Laskin, M., Srinivas, A., Abbeel, P.: CURL: contrastive unsupervised representations for reinforcement learning. In: International conference on machine learning, pp. 5639\u20135650 (2020)"},{"key":"9_CR24","unstructured":"Li, J., et al.: Open-world reinforcement learning over long short-term imagination. In: International Conference on Learning Representations (2025)"},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"Liotet, P., Vidaich, F., Metelli, A.M., Restelli, M.: Lifelong hyper-policy optimization with multiple importance sampling regularization. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 7525\u20137533. No.\u00a07 (2022)","DOI":"10.1609\/aaai.v36i7.20717"},{"key":"9_CR26","unstructured":"Liu, B., Liu, X., Jin, X., Stone, P., Liu, Q.: Conflict-averse gradient descent for multi-task learning. In: Advances in Neural Information Processing Systems, pp. 18878\u201318890 (2021)"},{"key":"9_CR27","unstructured":"Mendez, J.A., Eaton, E.: How to reuse and compose knowledge for a lifetime of tasks: a survey on continual learning and functional composition. arXiv preprint arXiv:2207.07730 (2022)"},{"key":"9_CR28","unstructured":"Mendez, J.A., van Seijen, H., Eaton, E.: Modular lifelong reinforcement learning via neural composition. arXiv preprint arXiv:2207.00429 (2022)"},{"key":"9_CR29","unstructured":"Pan, M., Zhu, X., Wang, Y., Yang, X.: Iso-dream: Isolating and leveraging noncontrollable visual dynamics in world models. In: Advances in Neural Information Processing Systems (2022)"},{"key":"9_CR30","unstructured":"Powers, S., Xing, E., Kolve, E., Mottaghi, R., Gupta, A.: Cora: benchmarks, baselines, and metrics as a platform for continual reinforcement learning agents. In: Conference on Lifelong Learning Agents, pp. 705\u2013743 (2022)"},{"key":"9_CR31","unstructured":"Rao, D., Visin, F., Rusu, A.A., Teh, Y.W., Pascanu, R., Hadsell, R.: Continual unsupervised representation learning. In: Advances in Neural Information Processing Systems (2019)"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Riemer, M., Klinger, T., Bouneffouf, D., Franceschini, M.: Scalable recollections for continual lifelong learning. In: Proceedings of the AAAI conference on artificial intelligence. vol.\u00a033, pp. 1352\u20131359 (2019)","DOI":"10.1609\/aaai.v33i01.33011352"},{"key":"9_CR33","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 (2020)"},{"key":"9_CR34","unstructured":"Shi, G., Azizzadenesheli, K., O\u2019Connell, M., Chung, S.J., Yue, Y.: Meta-adaptive nonlinear control: Theory and algorithms. In: Advances in Neural Information Processing Systems, pp. 10013\u201310025 (2021)"},{"key":"9_CR35","unstructured":"Sun, R., Zang, H., Li, X., Islam, R.: Learning latent dynamic robust representations for world models. In: ICML (2024)"},{"key":"9_CR36","unstructured":"Tassa, Y., et\u00a0al.: Deepmind control suite. arXiv preprint arXiv:1801.00690 (2018)"},{"key":"9_CR37","unstructured":"Wolczyk, M., Zajac, M., Pascanu, R., Kucinski, L., Milos, P.: Continual world: a robotic benchmark for continual reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 28496\u201328510 (2021)"},{"key":"9_CR38","unstructured":"Xie, A., Finn, C.: Lifelong robotic reinforcement learning by retaining experiences. In: Conference on Lifelong Learning Agents, pp. 838\u2013855 (2022)"},{"key":"9_CR39","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":"9_CR40","unstructured":"Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., Finn, C.: Gradient surgery for multi-task learning. In: Advances in Neural Information Processing Systems, pp. 5824\u20135836 (2020)"},{"key":"9_CR41","unstructured":"Yu, T., et al.: Meta-world: a benchmark and evaluation for multi-task and meta reinforcement learning. In: Conference on robot learning, vol.\u00a0100, pp. 1094\u20131100 (2019)"},{"key":"9_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, T., Wang, X., Liang, B., Yuan, B.: Catastrophic interference in reinforcement learning: a solution based on context division and knowledge distillation. In: IEEE Transactions on Neural Networks and Learning Systems (2022)","DOI":"10.36227\/techrxiv.15105492.v1"},{"key":"9_CR43","unstructured":"Zhou, W., et al.: Forgetting and imbalance in robot lifelong learning with off-policy data. In: Conference on Lifelong Learning Agents, pp. 294\u2013309 (2022)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06106-5_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T10:09:26Z","timestamp":1759399766000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06106-5_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,3]]},"ISBN":["9783032061058","9783032061065"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06106-5_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,3]]},"assertion":[{"value":"3 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}