{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T11:03:28Z","timestamp":1778411008725,"version":"3.51.4"},"reference-count":217,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T00:00:00Z","timestamp":1753660800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T00:00:00Z","timestamp":1753660800000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s11263-025-02472-w","type":"journal-article","created":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T06:42:21Z","timestamp":1753684941000},"page":"7368-7405","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning"],"prefix":"10.1007","volume":"133","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1884-6103","authenticated-orcid":false,"given":"Guozheng","family":"Ma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhecheng","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueqian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,28]]},"reference":[{"key":"2472_CR1","unstructured":"Abbas Z, Zhao R, Modayil J, White A, Machado MC (2023) Loss of plasticity in continual deep reinforcement learning. In: Conference on Lifelong Learning Agents, PMLR, pp 620\u2013636"},{"key":"2472_CR2","unstructured":"Ahn H, Hyeon J, Oh Y, Hwang B, Moon T (2024) Reset & distill: A recipe for overcoming negative transfer in continual reinforcement learning. arXiv preprint arXiv:2403.05066"},{"key":"2472_CR3","unstructured":"Almuzairee A, Hansen N, Christensen HI (2024) A recipe for unbounded data augmentation in visual reinforcement learning. arXiv preprint arXiv:2405.17416"},{"key":"2472_CR4","unstructured":"Anand A, Racah E, Ozair S, Bengio Y, C\u00f4t\u00e9 MA, Hjelm RD (2019) Unsupervised state representation learning in atari. Advances in neural information processing systems"},{"key":"2472_CR5","unstructured":"Antoniou A (2017) Data augmentation generative adversarial networks. arXiv preprint arXiv:1711.04340"},{"key":"2472_CR6","first-page":"3884","volume":"33","author":"J Ash","year":"2020","unstructured":"Ash, J., & Adams, R. P. (2020). On warm-starting neural network training. Advances in neural information processing systems, 33, 3884\u20133894.","journal-title":"Advances in neural information processing systems"},{"key":"2472_CR7","unstructured":"Auer P (2002) Using confidence bounds for exploitation-exploration trade-offs. Journal of Machine Learning Research 3(Nov):397\u2013422"},{"key":"2472_CR8","unstructured":"Balestriero R, Bottou L, LeCun Y (2022a) The effects of regularization and data augmentation are class dependent. arXiv preprint arXiv:2204.03632"},{"key":"2472_CR9","unstructured":"Balestriero R, Misra I, LeCun Y (2022b) A data-augmentation is worth a thousand samples: Exact quantification from analytical augmented sample moments. arXiv preprint arXiv:2202.08325"},{"key":"2472_CR10","unstructured":"Beattie C, Leibo JZ, Teplyashin D, Ward T, Wainwright M, K\u00fcttler H, Lefrancq A, Green S, Vald\u00e9s V, Sadik A, et\u00a0al. (2016) Deepmind lab. arXiv preprint arXiv:1612.03801"},{"key":"2472_CR11","unstructured":"Bellemare M, Dabney W, Dadashi R, Ali\u00a0Taiga A, Castro PS, Le\u00a0Roux N, Schuurmans D, Lattimore T, Lyle C (2019) A geometric perspective on optimal representations for reinforcement learning. Advances in neural information processing systems 32"},{"key":"2472_CR12","unstructured":"Benton G, Finzi M, Izmailov P, Wilson AG (2020) Learning invariances in neural networks. Advances in Neural Information Processing Systems 2020"},{"key":"2472_CR13","unstructured":"Bertoin D, Rachelson E (2022) Local feature swapping for generalization in reinforcement learning. arXiv preprint arXiv:2204.06355"},{"key":"2472_CR14","unstructured":"Botev A, Bauer M, De S (2022) Regularising for invariance to data augmentation improves supervised learning. arXiv preprint arXiv:2203.03304"},{"key":"2472_CR15","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020). Language models are few-shot learners. Advances in neural information processing systems, 33, 1877\u20131901.","journal-title":"Advances in neural information processing systems"},{"key":"2472_CR16","doi-asserted-by":"publisher","unstructured":"Chen C, Li J, Han X, Liu X, Yu Y (2022) Compound domain generalization via meta-knowledge encoding. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 7109\u20137119, https:\/\/doi.org\/10.1109\/CVPR52688.2022.00698","DOI":"10.1109\/CVPR52688.2022.00698"},{"key":"2472_CR17","unstructured":"Chen X, Hu J, Jin C, Li L, Wang L (2021) Understanding domain randomization for sim-to-real transfer. arXiv preprint arXiv:2110.03239"},{"key":"2472_CR18","doi-asserted-by":"crossref","unstructured":"Chen Z, Kiami S, Gupta A, Kumar V (2023) Genaug: Retargeting behaviors to unseen situations via generative augmentation. arXiv preprint arXiv:2302.06671","DOI":"10.15607\/RSS.2023.XIX.010"},{"key":"2472_CR19","doi-asserted-by":"crossref","unstructured":"Chen Z, Mandi Z, Bharadhwaj H, Sharma M, Song S, Gupta A, Kumar V (2024) Semantically controllable augmentations for generalizable robot learning. arXiv preprint arXiv:2409.00951","DOI":"10.1177\/02783649241273686"},{"key":"2472_CR20","unstructured":"Chepurko N, Marcus R, Zgraggen E, Fernandez RC, Kraska T, Karger D (2020) Arda: automatic relational data augmentation for machine learning. Proceedings of the VLDB Endowment"},{"key":"2472_CR21","unstructured":"Cheung TH, Yeung DY (2020) Modals: Modality-agnostic automated data augmentation in the latent space. In: International Conference on Learning Representations"},{"key":"2472_CR22","doi-asserted-by":"crossref","unstructured":"Choi J, Kim T, Kim C (2019) Self-ensembling with gan-based data augmentation for domain adaptation in semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 6830\u20136840","DOI":"10.1109\/ICCV.2019.00693"},{"key":"2472_CR23","unstructured":"Cobbe K, Klimov O, Hesse C, Kim T, Schulman J (2019) Quantifying generalization in reinforcement learning. In: International Conference on Machine Learning, PMLR"},{"key":"2472_CR24","unstructured":"Cobbe K, Hesse C, Hilton J, Schulman J (2020) Leveraging procedural generation to benchmark reinforcement learning. In: International conference on machine learning, PMLR"},{"key":"2472_CR25","doi-asserted-by":"crossref","unstructured":"Cubuk ED, Zoph B, Mane D, Vasudevan V, Le QV (2019) Autoaugment: Learning augmentation strategies from data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 113\u2013123","DOI":"10.1109\/CVPR.2019.00020"},{"key":"2472_CR26","unstructured":"Dablain DA, Chawla NV (2023) Towards understanding how data augmentation works with imbalanced data. arXiv preprint arXiv:2304.05895"},{"key":"2472_CR27","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, Ieee, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2472_CR28","unstructured":"DeVries T, Taylor GW (2017a) Dataset augmentation in feature space. arXiv preprint arXiv:1702.05538"},{"key":"2472_CR29","unstructured":"DeVries T, Taylor GW (2017b) Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552"},{"issue":"3","key":"2472_CR30","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1145\/212094.212114","volume":"27","author":"T Dietterich","year":"1995","unstructured":"Dietterich, T. (1995). Overfitting and undercomputing in machine learning. ACM computing surveys (CSUR), 27(3), 326\u2013327.","journal-title":"ACM computing surveys (CSUR)"},{"key":"2472_CR31","unstructured":"Doshi-Velez F, Konidaris G (2016) Hidden parameter markov decision processes: A semiparametric regression approach for discovering latent task parametrizations. In: IJCAI: proceedings of the conference, NIH Public Access, vol 2016, p 1432"},{"key":"2472_CR32","unstructured":"Du S, Krishnamurthy A, Jiang N, Agarwal A, Dudik M, Langford J (2019) Provably efficient rl with rich observations via latent state decoding. In: International Conference on Machine Learning, PMLR, pp 1665\u20131674"},{"key":"2472_CR33","unstructured":"Dubey A, Jauhri A, Pandey A, Kadian A, Al-Dahle A, Letman A, Mathur A, Schelten A, Yang A, Fan A, et\u00a0al. (2024) The llama 3 herd of models. arXiv preprint arXiv:2407.21783"},{"key":"2472_CR34","unstructured":"Fan J, Li W (2022) Dribo: Robust deep reinforcement learning via multi-view information bottleneck. In: International Conference on Machine Learning, PMLR, pp 6074\u20136102"},{"key":"2472_CR35","unstructured":"Fan L, Wang G, Huang DA, Yu Z, Fei-Fei L, Zhu Y, Anandkumar A (2021) Secant: Self-expert cloning for zero-shot generalization of visual policies. In: International Conference on Machine Learning"},{"key":"2472_CR36","unstructured":"Farebrother J, Machado MC, Bowling M (2018) Generalization and regularization in dqn. arXiv preprint arXiv:1810.00123"},{"key":"2472_CR37","unstructured":"Federici M, Dutta A, Forr\u00e9 P, Kushman N, Akata Z (2020) Learning robust representations via multi-view information bottleneck. arXiv preprint arXiv:2002.07017"},{"key":"2472_CR38","doi-asserted-by":"crossref","unstructured":"Feng SY, Gangal V, Wei J, Chandar S, Vosoughi S, Mitamura T, Hovy E (2021) A survey of data augmentation approaches for nlp. arXiv preprint arXiv:2105.03075","DOI":"10.18653\/v1\/2021.findings-acl.84"},{"key":"2472_CR39","unstructured":"Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: International conference on machine learning, PMLR, pp 1126\u20131135"},{"key":"2472_CR40","doi-asserted-by":"crossref","unstructured":"Fran\u00e7ois-Lavet V, Henderson P, Islam R, Bellemare MG, Pineau J, et\u00a0al. (2018) An introduction to deep reinforcement learning. Foundations and Trends\u00ae in Machine Learning 11(3-4):219\u2013354","DOI":"10.1561\/2200000071"},{"key":"2472_CR41","unstructured":"Ghosh D, Rahme J, Kumar A, Zhang A, Adams RP, Levine S (2021) Why generalization in rl is difficult: Epistemic pomdps and implicit partial observability. Advances in Neural Information Processing Systems 34"},{"key":"2472_CR42","first-page":"1199","volume-title":"2021 21st International Conference on Control","author":"Y Gil","year":"2021","unstructured":"Gil, Y., Baek, J., Park, J., & Han, S. (2021). Automatic data augmentation by upper confidence bounds for deep reinforcement learning. 2021 21st International Conference on Control (pp. 1199\u20131203). Automation and Systems (ICCAS): IEEE."},{"key":"2472_CR43","unstructured":"Golatkar AS, Achille A, Soatto S (2019) Time matters in regularizing deep networks: Weight decay and data augmentation affect early learning dynamics, matter little near convergence. Advances in Neural Information Processing Systems"},{"key":"2472_CR44","doi-asserted-by":"crossref","unstructured":"Gong C, Wang D, Li M, Chandra V, Liu Q (2021) Keepaugment: A simple information-preserving data augmentation approach. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 1055\u20131064","DOI":"10.1109\/CVPR46437.2021.00111"},{"key":"2472_CR45","unstructured":"Greydanus S, Koul A, Dodge J, Fern A (2018) Visualizing and understanding atari agents. In: International conference on machine learning, PMLR, pp 1792\u20131801"},{"key":"2472_CR46","unstructured":"Grigsby J, Qi Y (2020) Measuring visual generalization in continuous control from pixels. arXiv preprint arXiv:2010.06740"},{"key":"2472_CR47","unstructured":"Guan L, Verma M, Guo S, Zhang R, Kambhampati S (2021) Widening the pipeline in human-guided reinforcement learning with explanation and context-aware data augmentation. Advances in Neural Information Processing Systems"},{"key":"2472_CR48","unstructured":"Haarnoja T, Zhou A, Abbeel P, Levine S (2018) Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International conference on machine learning, PMLR, pp 1861\u20131870"},{"key":"2472_CR49","unstructured":"Hafner D, Lillicrap T, Ba J, Norouzi M (2019a) Dream to control: Learning behaviors by latent imagination. In: International Conference on Learning Representations"},{"key":"2472_CR50","unstructured":"Hafner D, Lillicrap T, Fischer I, Villegas R, Ha D, Lee H, Davidson J (2019b) Learning latent dynamics for planning from pixels. In: International conference on machine learning, PMLR, pp 2555\u20132565"},{"key":"2472_CR51","unstructured":"Hafner D, Lillicrap TP, Norouzi M, Ba J (2020) Mastering atari with discrete world models. In: International Conference on Learning Representations"},{"key":"2472_CR52","unstructured":"Hallak A, Di\u00a0Castro D, Mannor S (2015) Contextual markov decision processes. arXiv preprint arXiv:1502.02259"},{"key":"2472_CR53","unstructured":"Han B, Zheng C, Chan H, Paster K, Zhang M, Ba J (2021) Learning domain invariant representations in goal-conditioned block mdps. Advances in Neural Information Processing Systems 34"},{"key":"2472_CR54","doi-asserted-by":"crossref","unstructured":"Hansen N, Wang X (2021) Generalization in reinforcement learning by soft data augmentation. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), IEEE, pp 13611\u201313617","DOI":"10.1109\/ICRA48506.2021.9561103"},{"key":"2472_CR55","unstructured":"Hansen N, Su H, Wang X (2021) Stabilizing deep q-learning with convnets and vision transformers under data augmentation. Advances in Neural Information Processing Systems 34"},{"key":"2472_CR56","unstructured":"Hansen S, Dabney W, Barreto A, Van\u00a0de Wiele T, Warde-Farley D, Mnih V (2019) Fast task inference with variational intrinsic successor features. arXiv preprint arXiv:1906.05030"},{"key":"2472_CR57","unstructured":"Hausknecht M, Stone P (2015) Deep recurrent q-learning for partially observable mdps. In: 2015 aaai fall symposium series"},{"key":"2472_CR58","unstructured":"Hausknecht M, Wagener N (2022) Consistent dropout for policy gradient reinforcement learning. arXiv preprint arXiv:2202.11818"},{"key":"2472_CR59","unstructured":"He H, Bai C, Xu K, Yang Z, Zhang W, Wang D, Zhao B, Li X (2024) Diffusion model is an effective planner and data synthesizer for multi-task reinforcement learning. Advances in neural information processing systems 36"},{"key":"2472_CR60","doi-asserted-by":"crossref","unstructured":"He K, Fan H, Wu Y, Xie S, Girshick R (2020) Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"2472_CR61","doi-asserted-by":"crossref","unstructured":"He K, Chen X, Xie S, Li Y, Doll\u00e1r P, Girshick R (2021a) Masked autoencoders are scalable vision learners. arXiv preprint arXiv:2111.06377","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"2472_CR62","unstructured":"He T, Zhang Y, Ren K, Wang C, Zhang W, Li D, Yang Y (2021b) Aarl: Automated auxiliary loss for reinforcement learning. openreviewnet"},{"key":"2472_CR63","unstructured":"He T, Zhang Y, Ren K, Liu M, Wang C, Zhang W, Yang Y, Li D (2022) Reinforcement learning with automated auxiliary loss search. arXiv preprint arXiv:2210.06041"},{"key":"2472_CR64","unstructured":"Hendrycks D, Mu N, Cubuk ED, Zoph B, Gilmer J, Lakshminarayanan B (2019) Augmix: A simple data processing method to improve robustness and uncertainty. arXiv preprint arXiv:1912.02781"},{"key":"2472_CR65","unstructured":"Hern\u00e1ndez-Garc\u00eda A, K\u00f6nig P (2018) Data augmentation instead of explicit regularization. arXiv preprint arXiv:1806.03852"},{"issue":"2","key":"2472_CR66","doi-asserted-by":"publisher","first-page":"1225","DOI":"10.1109\/TRO.2022.3207619","volume":"39","author":"D Horv\u00e1th","year":"2022","unstructured":"Horv\u00e1th, D., Erd\u0151s, G., Istenes, Z., Horv\u00e1th, T., & F\u00f6ldi, S. (2022). Object detection using sim2real domain randomization for robotic applications. IEEE Transactions on Robotics, 39(2), 1225\u20131243.","journal-title":"IEEE Transactions on Robotics"},{"key":"2472_CR67","unstructured":"Hu J, Jiang Y, Weng P (2024) Revisiting data augmentation in deep reinforcement learning. In: The Twelfth International Conference on Learning Representations,https:\/\/openreview.net\/forum?id=EGQBpkIEuu"},{"key":"2472_CR68","unstructured":"Huang T, Wang J, Chen X (2022) Accelerating representation learning with view-consistent dynamics in data-efficient reinforcement learning. arXiv preprint arXiv:2201.07016"},{"key":"2472_CR69","unstructured":"Huang W, Yi M, Zhao X (2021) Towards the generalization of contrastive self-supervised learning. arXiv preprint arXiv:2111.00743"},{"key":"2472_CR70","doi-asserted-by":"crossref","unstructured":"Huang X, Belongie S (2017) Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE international conference on computer vision, pp 1501\u20131510","DOI":"10.1109\/ICCV.2017.167"},{"key":"2472_CR71","doi-asserted-by":"crossref","unstructured":"Huber J, H\u00e9l\u00e9non F, Watrelot H, Amar FB, Doncieux S (2024) Domain randomization for sim2real transfer of automatically generated grasping datasets. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), IEEE, pp 4112\u20134118","DOI":"10.1109\/ICRA57147.2024.10610677"},{"key":"2472_CR72","unstructured":"Igl M, Ciosek K, Li Y, Tschiatschek S, Zhang C, Devlin S, Hofmann K (2019) Generalization in reinforcement learning with selective noise injection and information bottleneck. Advances in neural information processing systems 32"},{"key":"2472_CR73","unstructured":"Immer A, van\u00a0der Ouderaa TF, Fortuin V, R\u00e4tsch G, van\u00a0der Wilk M (2022) Invariance learning in deep neural networks with differentiable laplace approximations. arXiv preprint arXiv:2202.10638"},{"key":"2472_CR74","unstructured":"Imre B (2021) An investigation of generative replay in deep reinforcement learning. B.S. thesis, University of Twente"},{"key":"2472_CR75","unstructured":"Kaiser L, Babaeizadeh M, Milos P, Osinski B, Campbell RH, Czechowski K, Erhan D, Finn C, Kozakowski P, Levine S, et\u00a0al. (2019) Model-based reinforcement learning for atari. arXiv preprint arXiv:1903.00374"},{"key":"2472_CR76","unstructured":"Kalashnikov D, Irpan A, Pastor P, Ibarz J, Herzog A, Jang E, Quillen D, Holly E, Kalakrishnan M, Vanhoucke V, et\u00a0al. (2018) Scalable deep reinforcement learning for vision-based robotic manipulation. In: Conference on Robot Learning, PMLR"},{"key":"2472_CR77","first-page":"4764","volume":"34","author":"M Kemertas","year":"2021","unstructured":"Kemertas, M., & Aumentado-Armstrong, T. (2021). Towards robust bisimulation metric learning. Advances in Neural Information Processing Systems, 34, 4764\u20134777.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2472_CR78","doi-asserted-by":"crossref","unstructured":"Khalifa NE, Loey M, Mirjalili S (2021) A comprehensive survey of recent trends in deep learning for digital images augmentation. Artificial Intelligence Review pp 1\u201327","DOI":"10.1007\/s10462-021-10066-4"},{"key":"2472_CR79","unstructured":"Kim J, Park S, Levine S (2024a) Unsupervised-to-online reinforcement learning. arXiv preprint arXiv:2408.14785"},{"issue":"3","key":"2472_CR80","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0265456","volume":"17","author":"M Kim","year":"2022","unstructured":"Kim, M., Rho, K., Kim, Yd., & Jung, K. (2022). Action-driven contrastive representation for reinforcement learning. Plos one, 17(3), Article e0265456.","journal-title":"Plos one"},{"key":"2472_CR81","unstructured":"Kim MJ, Pertsch K, Karamcheti S, Xiao T, Balakrishna A, Nair S, Rafailov R, Foster E, Lam G, Sanketi P, et\u00a0al. (2024b) Openvla: An open-source vision-language-action model. arXiv preprint arXiv:2406.09246"},{"key":"2472_CR82","doi-asserted-by":"crossref","unstructured":"Kiran BR, Sobh I, Talpaert V, Mannion P, Al\u00a0Sallab AA, Yogamani S, P\u00e9rez P (2021) Deep reinforcement learning for autonomous driving: A survey. IEEE Transactions on Intelligent Transportation Systems","DOI":"10.1109\/TITS.2021.3054625"},{"key":"2472_CR83","unstructured":"Kirk R, Zhang A, Grefenstette E, Rockt\u00e4schel T (2021) A survey of generalisation in deep reinforcement learning. arXiv preprint arXiv:2111.09794"},{"key":"2472_CR84","unstructured":"Ko B, Ok J (2021) Time matters in using data augmentation for vision-based deep reinforcement learning. arXiv preprint arXiv:2102.08581"},{"key":"2472_CR85","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25, 1097\u20131105.","journal-title":"Advances in neural information processing systems"},{"key":"2472_CR86","unstructured":"Kumar S, Marklund H, Van\u00a0Roy B (2023) Maintaining plasticity via regenerative regularization. arXiv preprint arXiv:2308.11958"},{"key":"2472_CR87","unstructured":"Lambert N, Wulfmeier M, Whitney W, Byravan A, Bloesch M, Dasagi V, Hertweck T, Riedmiller M (2022) The challenges of exploration for offline reinforcement learning. arXiv preprint arXiv:2201.11861"},{"key":"2472_CR88","first-page":"19884","volume":"33","author":"M Laskin","year":"2020","unstructured":"Laskin, M., Lee, K., Stooke, A., Pinto, L., Abbeel, P., & Srinivas, A. (2020). Reinforcement learning with augmented data. Advances in neural information processing systems, 33, 19884\u201319895.","journal-title":"Advances in neural information processing systems"},{"key":"2472_CR89","unstructured":"Laskin M, Srinivas A, Abbeel P (2020b) Curl: Contrastive unsupervised representations for reinforcement learning. In: International Conference on Machine Learning, PMLR, pp 5639\u20135650"},{"key":"2472_CR90","unstructured":"Laskin M, Yarats D, Liu H, Lee K, Zhan A, Lu K, Cang C, Pinto L, Abbeel P (2021) Urlb: Unsupervised reinforcement learning benchmark. arXiv preprint arXiv:2110.15191"},{"key":"2472_CR91","unstructured":"Laskin M, Liu H, Peng XB, Yarats D, Rajeswaran A, Abbeel P (2022) Cic: Contrastive intrinsic control for unsupervised skill discovery. arXiv preprint arXiv:2202.00161"},{"key":"2472_CR92","first-page":"741","volume":"33","author":"AX Lee","year":"2020","unstructured":"Lee, A. X., Nagabandi, A., Abbeel, P., & Levine, S. (2020). Stochastic latent actor-critic: Deep reinforcement learning with a latent variable model. Advances in Neural Information Processing Systems, 33, 741\u2013752.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2472_CR93","unstructured":"Lee K, Lee K, Shin J, Lee H (2019) Network randomization: A simple technique for generalization in deep reinforcement learning. arXiv preprint arXiv:1910.05396"},{"key":"2472_CR94","first-page":"11890","volume":"33","author":"KH Lee","year":"2020","unstructured":"Lee, K. H., Fischer, I., Liu, A., Guo, Y., Lee, H., Canny, J., & Guadarrama, S. (2020). Predictive information accelerates learning in rl. Advances in Neural Information Processing Systems, 33, 11890\u201311901.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2472_CR95","unstructured":"Lee S, Seo Y, Lee K, Abbeel P, Shin J (2022) Offline-to-online reinforcement learning via balanced replay and pessimistic q-ensemble. In: Conference on Robot Learning, PMLR, pp 1702\u20131712"},{"key":"2472_CR96","unstructured":"Li L, Lyu J, Ma G, Wang Z, Yang Z, Li X, Li Z (2024a) Normalization enhances generalization in visual reinforcement learning. In: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems, pp 1137\u20131146"},{"key":"2472_CR97","unstructured":"Li X, Shang J, Das S, Ryoo MS (2022) Does self-supervised learning really improve reinforcement learning from pixels? arXiv preprint arXiv:2206.05266"},{"key":"2472_CR98","doi-asserted-by":"crossref","unstructured":"Li Y, Hu G, Wang Y, Hospedales T, Robertson NM, Yang Y (2020) Differentiable automatic data augmentation. In: European Conference on Computer Vision, Springer, pp 580\u2013595","DOI":"10.1007\/978-3-030-58542-6_35"},{"key":"2472_CR99","unstructured":"Li Z, Lu Y, Mu Y, Qiao H (2024b) Cog-ga: A large language models-based generative agent for vision-language navigation in continuous environments. arXiv preprint arXiv:2409.02522"},{"key":"2472_CR100","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, Heess N, Erez T, Tassa Y, Silver D, Wierstra D (2015) Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971"},{"key":"2472_CR101","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: Common objects in context. In: European conference on computer vision, Springer, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"4","key":"2472_CR102","doi-asserted-by":"publisher","first-page":"6615","DOI":"10.1109\/LRA.2020.3013937","volume":"5","author":"Y Lin","year":"2020","unstructured":"Lin, Y., Huang, J., Zimmer, M., Guan, Y., Rojas, J., & Weng, P. (2020). Invariant transform experience replay: Data augmentation for deep reinforcement learning. IEEE Robotics and Automation Letters, 5(4), 6615\u20136622.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"2472_CR103","unstructured":"Liu H, Abbeel P (2021a) Aps: Active pretraining with successor features. In: International Conference on Machine Learning, PMLR, pp 6736\u20136747"},{"key":"2472_CR104","unstructured":"Liu H, Abbeel P (2021b) Behavior from the void: Unsupervised active pre-training. Advances in Neural Information Processing Systems 34"},{"key":"2472_CR105","doi-asserted-by":"crossref","unstructured":"Liu M, Zhu Y, Chen Y, Zhao D (2024) Enhancing reinforcement learning via transformer-based state predictive representations. IEEE Transactions on Artificial Intelligence","DOI":"10.1109\/TAI.2024.3379969"},{"key":"2472_CR106","doi-asserted-by":"crossref","unstructured":"Liu X, Zou Y, Kong L, Diao Z, Yan J, Wang J, Li S, Jia P, You J (2018) Data augmentation via latent space interpolation for image classification. In: 2018 24th International Conference on Pattern Recognition (ICPR), IEEE, pp 728\u2013733","DOI":"10.1109\/ICPR.2018.8545506"},{"key":"2472_CR107","unstructured":"Liu Z, Li X, Kang B, Darrell T (2020) Regularization matters in policy optimization-an empirical study on continuous control. In: International Conference on Learning Representations"},{"key":"2472_CR108","unstructured":"Lu C, Huang B, Wang K, Hern\u00e1ndez-Lobato JM, Zhang K, Sch\u00f6lkopf B (2020) Sample-efficient reinforcement learning via counterfactual-based data augmentation. arXiv preprint arXiv:2012.09092"},{"key":"2472_CR109","unstructured":"Lu C, Ball P, Teh YW, Parker-Holder J (2024) Synthetic experience replay. Advances in Neural Information Processing Systems 36"},{"key":"2472_CR110","unstructured":"Lyle C, Zheng Z, Nikishin E, Pires BA, Pascanu R, Dabney W (2023) Understanding plasticity in neural networks. In: International Conference on Machine Learning, PMLR, pp 23190\u201323211"},{"key":"2472_CR111","unstructured":"Lyle C, Zheng Z, Khetarpal K, Martens J, van Hasselt H, Pascanu R, Dabney W (2024) Normalization and effective learning rates in reinforcement learning. arXiv preprint arXiv:2407.01800"},{"key":"2472_CR112","unstructured":"Ma G, Li L, Zhang S, Liu Z, Wang Z, Chen Y, Shen L, Wang X, Tao D (2024a) Revisiting plasticity in visual reinforcement learning: Data, modules and training stages. In: The Twelfth International Conference on Learning Representations, https:\/\/openreview.net\/forum?id=0aR1s9YxoL"},{"key":"2472_CR113","unstructured":"Ma G, Zhang L, Wang H, Li L, Wang Z, Wang Z, Shen L, Wang X, Tao D (2024b) Learning better with less: Effective augmentation for sample-efficient visual reinforcement learning. Advances in Neural Information Processing Systems 36"},{"key":"2472_CR114","unstructured":"Ma Y, Song Z, Zhuang Y, Hao J, King I (2024c) A survey on vision-language-action models for embodied ai. arXiv preprint arXiv:2405.14093"},{"key":"2472_CR115","unstructured":"Mandi Z, Bharadhwaj H, Moens V, Song S, Rajeswaran A, Kumar V (2022) Cacti: A framework for scalable multi-task multi-scene visual imitation learning. arXiv preprint arXiv:2212.05711"},{"key":"2472_CR116","doi-asserted-by":"crossref","unstructured":"Mansourifar H, Chen L, Shi W (2019) Virtual big data for gan based data augmentation. In: 2019 IEEE International Conference on Big Data (Big Data), IEEE, pp 1478\u20131487","DOI":"10.1109\/BigData47090.2019.9006268"},{"key":"2472_CR117","unstructured":"Mazoure B, Tachet\u00a0des Combes R, Doan TL, Bachman P, Hjelm RD (2020) Deep reinforcement and infomax learning. In: Advances in Neural Information Processing Systems"},{"key":"2472_CR118","unstructured":"Mehta B, Diaz M, Golemo F, Pal CJ, Paull L (2020) Active domain randomization. In: Conference on Robot Learning, PMLR, pp 1162\u20131176"},{"key":"2472_CR119","unstructured":"Mei S, Misiakiewicz T, Montanari A (2021) Learning with invariances in random features and kernel models. In: Conference on Learning Theory, PMLR, pp 3351\u20133418"},{"key":"2472_CR120","doi-asserted-by":"crossref","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G, et\u00a0al. (2015) Human-level control through deep reinforcement learning. nature 518(7540):529\u2013533","DOI":"10.1038\/nature14236"},{"issue":"6","key":"2472_CR121","doi-asserted-by":"publisher","first-page":"3947","DOI":"10.1007\/s10462-019-09784-7","volume":"53","author":"R Moradi","year":"2020","unstructured":"Moradi, R., Berangi, R., & Minaei, B. (2020). A survey of regularization strategies for deep models. Artificial Intelligence Review, 53(6), 3947\u20133986.","journal-title":"Artificial Intelligence Review"},{"key":"2472_CR122","doi-asserted-by":"crossref","unstructured":"Moreno-Barea FJ, Strazzera F, Jerez JM, Urda D, Franco L (2018) Forward noise adjustment scheme for data augmentation. In: 2018 IEEE symposium series on computational intelligence (SSCI), IEEE, pp 728\u2013734","DOI":"10.1109\/SSCI.2018.8628917"},{"key":"2472_CR123","unstructured":"Mott A, Zoran D, Chrzanowski M, Wierstra D, Jimenez\u00a0Rezende D (2019) Towards interpretable reinforcement learning using attention augmented agents. Advances in Neural Information Processing Systems 32"},{"key":"2472_CR124","unstructured":"Mu Y, Zhang Q, Hu M, Wang W, Ding M, Jin J, Wang B, Dai J, Qiao Y, Luo P (2023) Embodiedgpt: Vision-language pre-training via embodied chain of thought. In: Oh A, Naumann T, Globerson A, Saenko K, Hardt M, Levine S (eds) Advances in Neural Information Processing Systems, Curran Associates, Inc., vol\u00a036, pp 25081\u201325094, https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/4ec43957eda1126ad4887995d05fae3b-Paper-Conference.pdf"},{"key":"2472_CR125","unstructured":"Muratore F, Gruner T, Wiese F, Belousov B, Gienger M, Peters J (2022) Neural posterior domain randomization. In: Conference on Robot Learning, PMLR, pp 1532\u20131542"},{"key":"2472_CR126","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.clinimag.2020.04.025","volume":"65","author":"S Mutasa","year":"2020","unstructured":"Mutasa, S., Sun, S., & Ha, R. (2020). Understanding artificial intelligence based radiology studies: What is overfitting? Clinical imaging, 65, 96\u201399.","journal-title":"Clinical imaging"},{"key":"2472_CR127","unstructured":"Nair AV, Pong V, Dalal M, Bahl S, Lin S, Levine S (2018) Visual reinforcement learning with imagined goals. Advances in neural information processing systems 31"},{"key":"2472_CR128","unstructured":"Nakamoto M, Zhai S, Singh A, Sobol\u00a0Mark M, Ma Y, Finn C, Kumar A, Levine S (2024) Cal-ql: Calibrated offline rl pre-training for efficient online fine-tuning. Advances in Neural Information Processing Systems 36"},{"key":"2472_CR129","doi-asserted-by":"crossref","unstructured":"Nguyen T, Luu TM, Vu T, Yoo CD (2021) Sample-efficient reinforcement learning representation learning with curiosity contrastive forward dynamics model. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, pp 3471\u20133477","DOI":"10.1109\/IROS51168.2021.9636536"},{"key":"2472_CR130","unstructured":"Ni T, Eysenbach B, Seyedsalehi E, Ma M, Gehring C, Mahajan A, Bacon PL (2024) Bridging state and history representations: Understanding self-predictive rl. arXiv preprint arXiv:2401.08898"},{"key":"2472_CR131","unstructured":"Nikishin E, Schwarzer M, D\u2019Oro P, Bacon PL, Courville A (2022) The primacy bias in deep reinforcement learning. In: International conference on machine learning, PMLR, pp 16828\u201316847"},{"key":"2472_CR132","unstructured":"Nikishin E, Oh J, Ostrovski G, Lyle C, Pascanu R, Dabney W, Barreto A (2024) Deep reinforcement learning with plasticity injection. Advances in Neural Information Processing Systems 36"},{"key":"2472_CR133","unstructured":"Nozawa K, Sato I (2022) Empirical evaluation and theoretical analysis for representation learning: A survey. arXiv preprint arXiv:2204.08226"},{"issue":"11","key":"2472_CR134","doi-asserted-by":"publisher","first-page":"7999","DOI":"10.1007\/s00500-019-04094-0","volume":"24","author":"H Ohno","year":"2020","unstructured":"Ohno, H. (2020). Auto-encoder-based generative models for data augmentation on regression problems. Soft Computing, 24(11), 7999\u20138009.","journal-title":"Soft Computing"},{"key":"2472_CR135","unstructured":"Oord Avd, Li Y, Vinyals O (2018) Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748"},{"key":"2472_CR136","doi-asserted-by":"crossref","unstructured":"Pan F, Zhang T, Luo L, He J, Liu S (2022) Learn continuously, act discretely: Hybrid action-space reinforcement learning for optimal execution. In: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence (IJCAI-22), pp 3912\u20133918","DOI":"10.24963\/ijcai.2022\/543"},{"key":"2472_CR137","unstructured":"Parisi S, Rajeswaran A, Purushwalkam S, Gupta A (2022) The unsurprising effectiveness of pre-trained vision models for control. In: International Conference on Machine Learning, PMLR, pp 17359\u201317371"},{"key":"2472_CR138","doi-asserted-by":"crossref","unstructured":"Peng XB, Andrychowicz M, Zaremba W, Abbeel P (2018) Sim-to-real transfer of robotic control with dynamics randomization. In: 2018 IEEE international conference on robotics and automation (ICRA), IEEE, pp 3803\u20133810","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"2472_CR139","unstructured":"Prudencio RF, Maximo MR, Colombini EL (2023) A survey on offline reinforcement learning: Taxonomy, review, and open problems. IEEE Transactions on Neural Networks and Learning Systems"},{"key":"2472_CR140","unstructured":"Rafiee B, Jin J, Luo J, White A (2022) What makes useful auxiliary tasks in reinforcement learning: investigating the effect of the target policy. arXiv preprint arXiv:2204.00565"},{"key":"2472_CR141","first-page":"5402","volume":"34","author":"R Raileanu","year":"2021","unstructured":"Raileanu, R., Goldstein, M., Yarats, D., Kostrikov, I., & Fergus, R. (2021). Automatic data augmentation for generalization in reinforcement learning. Advances in Neural Information Processing Systems, 34, 5402\u20135415.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2472_CR142","first-page":"26345","volume":"34","author":"K Rakelly","year":"2021","unstructured":"Rakelly, K., Gupta, A., Florensa, C., & Levine, S. (2021). Which mutual-information representation learning objectives are sufficient for control? Advances in Neural Information Processing Systems, 34, 26345\u201326357.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2472_CR143","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347"},{"key":"2472_CR144","unstructured":"Schwarzer M, Anand A, Goel R, Hjelm RD, Courville A, Bachman P (2020) Data-efficient reinforcement learning with self-predictive representations. In: International Conference on Learning Representations"},{"key":"2472_CR145","unstructured":"Schwarzer M, Rajkumar N, Noukhovitch M, Anand A, Charlin L, Hjelm RD, Bachman P, Courville AC (2021) Pretraining representations for data-efficient reinforcement learning. Advances in Neural Information Processing Systems 34"},{"key":"2472_CR146","unstructured":"Schwarzer M, Ceron JSO, Courville A, Bellemare MG, Agarwal R, Castro PS (2023) Bigger, better, faster: Human-level atari with human-level efficiency. In: International Conference on Machine Learning, PMLR, pp 30365\u201330380"},{"key":"2472_CR147","unstructured":"Shah RM, Kumar V (2021) Rrl: Resnet as representation for reinforcement learning. In: International Conference on Machine Learning, PMLR, pp 9465\u20139476"},{"key":"2472_CR148","unstructured":"Shen L, Yang L, Chen S, Yuan B, Wang X, Tao D, et\u00a0al. (2022a) Penalized proximal policy optimization for safe reinforcement learning. arXiv preprint arXiv:2205.11814"},{"key":"2472_CR149","unstructured":"Shen R, Bubeck S, Gunasekar S (2022b) Data augmentation as feature manipulation. In: International conference on machine learning, PMLR, pp 19773\u201319808"},{"issue":"1","key":"2472_CR150","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. (2019). A survey on image data augmentation for deep learning. Journal of big data, 6(1), 1\u201348.","journal-title":"Journal of big data"},{"key":"2472_CR151","doi-asserted-by":"crossref","unstructured":"Silver D, Hubert T, Schrittwieser J, Antonoglou I, Lai M, Guez A, Lanctot M, Sifre L, Kumaran D, Graepel T, et\u00a0al. (2018) A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. Science 362","DOI":"10.1126\/science.aar6404"},{"key":"2472_CR152","unstructured":"Sodhani S, Meier F, Pineau J, Zhang A (2022) Block contextual mdps for continual learning. In: Learning for Dynamics and Control Conference, PMLR, pp 608\u2013623"},{"key":"2472_CR153","unstructured":"Sokar G, Agarwal R, Castro PS, Evci U (2023) The dormant neuron phenomenon in deep reinforcement learning. In: International Conference on Machine Learning, PMLR, pp 32145\u201332168"},{"key":"2472_CR154","unstructured":"Song X, Jiang Y, Tu S, Du Y, Neyshabur B (2019) Observational overfitting in reinforcement learning. In: International Conference on Learning Representations"},{"key":"2472_CR155","unstructured":"Stone A, Ramirez O, Konolige K, Jonschkowski R (2021) The distracting control suite\u2013a challenging benchmark for reinforcement learning from pixels. arXiv preprint arXiv:2101.02722"},{"key":"2472_CR156","unstructured":"Stooke A, Lee K, Abbeel P, Laskin M (2021) Decoupling representation learning from reinforcement learning. In: International Conference on Machine Learning, PMLR, pp 9870\u20139879"},{"key":"2472_CR157","doi-asserted-by":"crossref","unstructured":"Sun C, Qian H, Miao C (2022) Cclf: A contrastive-curiosity-driven learning framework for sample-efficient reinforcement learning. arXiv preprint arXiv:2205.00943","DOI":"10.24963\/ijcai.2022\/478"},{"key":"2472_CR158","unstructured":"Tan Z, Wang K, Wang X (2024) Implicit curriculum in procgen made explicit. In: The Thirty-eighth Annual Conference on Neural Information Processing Systems, https:\/\/openreview.net\/forum?id=nZB1FpXUU6"},{"key":"2472_CR159","doi-asserted-by":"crossref","unstructured":"Tang G, Rajkumar S, Zhou Y, Walke HR, Levine S, Fang K (2024) Kalie: Fine-tuning vision-language models for open-world manipulation without robot data. arXiv preprint arXiv:2409.14066","DOI":"10.1109\/ICRA55743.2025.11128156"},{"key":"2472_CR160","unstructured":"Tarasov D, Kurenkov V, Nikulin A, Kolesnikov S (2024) Revisiting the minimalist approach to offline reinforcement learning. Advances in Neural Information Processing Systems 36"},{"key":"2472_CR161","unstructured":"Tassa Y, Doron Y, Muldal A, Erez T, Li Y, Casas DdL, Budden D, Abdolmaleki A, Merel J, Lefrancq A, et\u00a0al. (2018) Deepmind control suite. arXiv preprint arXiv:1801.00690"},{"key":"2472_CR162","doi-asserted-by":"crossref","unstructured":"Tobin J, Fong R, Ray A, Schneider J, Zaremba W, Abbeel P (2017) 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), IEEE","DOI":"10.1109\/IROS.2017.8202133"},{"key":"2472_CR163","unstructured":"Tomar M, Mishra UA, Zhang A, Taylor ME (2021) Learning representations for pixel-based control: What matters and why? arXiv preprint arXiv:2111.07775"},{"key":"2472_CR164","unstructured":"Tschannen M, Djolonga J, Rubenstein PK, Gelly S, Lucic M (2019) On mutual information maximization for representation learning. arXiv preprint arXiv:1907.13625"},{"key":"2472_CR165","unstructured":"Von\u00a0K\u00fcgelgen J, Sharma Y, Gresele L, Brendel W, Sch\u00f6lkopf B, Besserve M, Locatello F (2021) Self-supervised learning with data augmentations provably isolates content from style. Advances in Neural Information Processing Systems 34"},{"key":"2472_CR166","unstructured":"Wang C, Luo X, Ross K, Li D (2022a) Vrl3: A data-driven framework for visual deep reinforcement learning. arXiv preprint arXiv:2202.10324"},{"key":"2472_CR167","unstructured":"Wang JX, Kurth-Nelson Z, Tirumala D, Soyer H, Leibo JZ, Munos R, Blundell C, Kumaran D, Botvinick M (2016a) Learning to reinforcement learn. arXiv preprint arXiv:1611.05763"},{"key":"2472_CR168","unstructured":"Wang K, Kang B, Shao J, Feng J (2020a) Improving generalization in reinforcement learning with mixture regularization. Advances in Neural Information Processing Systems"},{"key":"2472_CR169","unstructured":"Wang Q, Yang J, Wang Y, Jin X, Zeng W, Yang X (2023) Making offline rl online: Collaborative world models for offline visual reinforcement learning. arXiv preprint arXiv:2305.15260"},{"key":"2472_CR170","doi-asserted-by":"crossref","unstructured":"Wang X, Lian L, Yu SX (2021) Unsupervised visual attention and invariance for reinforcement learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 6677\u20136687","DOI":"10.1109\/CVPR46437.2021.00661"},{"key":"2472_CR171","unstructured":"Wang Z, Schaul T, Hessel M, Hasselt H, Lanctot M, Freitas N (2016b) Dueling network architectures for deep reinforcement learning. In: International conference on machine learning, PMLR, pp 1995\u20132003"},{"key":"2472_CR172","first-page":"9963","volume":"119","author":"Z Wang","year":"2020","unstructured":"Wang, Z., Liu, L., & Tao, D. (2020). Deep streaming label learning. International Conference on Machine Learning (ICML), 119, 9963\u20139972.","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"2472_CR173","doi-asserted-by":"crossref","unstructured":"Wang Z, Liu L, Duan Y, Kong Y, Tao D (2022b) Continual learning with lifelong vision transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 171\u2013181","DOI":"10.1109\/CVPR52688.2022.00027"},{"key":"2472_CR174","doi-asserted-by":"publisher","unstructured":"Wang Z, Liu L, Duan Y, Tao D (2022c) Sin: Semantic inference network for few-shot streaming label learning. IEEE Transactions on Neural Networks and Learning Systems pp 1\u201314, https:\/\/doi.org\/10.1109\/TNNLS.2022.3162747","DOI":"10.1109\/TNNLS.2022.3162747"},{"key":"2472_CR175","doi-asserted-by":"crossref","unstructured":"Wen X, Yu X, Yang R, Bai C, Wang Z (2023) Towards robust offline-to-online reinforcement learning via uncertainty and smoothness. arXiv preprint arXiv:2309.16973","DOI":"10.1613\/jair.1.16457"},{"key":"2472_CR176","unstructured":"Wen Z, Li Y (2021) Toward understanding the feature learning process of self-supervised contrastive learning. In: International Conference on Machine Learning, PMLR"},{"key":"2472_CR177","doi-asserted-by":"crossref","unstructured":"Wong SC, Gatt A, Stamatescu V, McDonnell MD (2016) Understanding data augmentation for classification: when to warp? In: 2016 international conference on digital image computing: techniques and applications (DICTA), IEEE, pp 1\u20136","DOI":"10.1109\/DICTA.2016.7797091"},{"key":"2472_CR178","doi-asserted-by":"crossref","unstructured":"Wu K, Wu M, Chen Z, Xu Y, Li X (2022) Generalizing reinforcement learning through fusing self-supervised learning into intrinsic motivation. The 36th AAAI Conference on Artificial Intelligence (AAAI 2022)","DOI":"10.1609\/aaai.v36i8.20847"},{"key":"2472_CR179","unstructured":"Xiao T, Radosavovic I, Darrell T, Malik J (2022) Masked visual pre-training for motor control. arXiv preprint arXiv:2203.06173"},{"key":"2472_CR180","doi-asserted-by":"crossref","unstructured":"Xingyi\u00a0Yang iW (2024) Neural metamorphosis. ECCV","DOI":"10.1007\/978-3-031-72754-2_1"},{"key":"2472_CR181","unstructured":"Xu G, Zheng R, Liang Y, Wang X, Yuan Z, Ji T, Luo Y, Liu X, Yuan J, Hua P, et\u00a0al. (2023) Drm: Mastering visual reinforcement learning through dormant ratio minimization. arXiv preprint arXiv:2310.19668"},{"key":"2472_CR182","doi-asserted-by":"crossref","unstructured":"Yan E, Huang Y (2021) Do cnns encode data augmentations? In: 2021 International Joint Conference on Neural Networks (IJCNN), IEEE, pp 1\u20138","DOI":"10.1109\/IJCNN52387.2021.9534219"},{"key":"2472_CR183","doi-asserted-by":"crossref","unstructured":"Yang R, Wang J, Geng Z, Ye M, Ji S, Li B, Wu F (2022a) Learning task-relevant representations for generalization via characteristic functions of reward sequence distributions. arXiv preprint arXiv:2205.10218","DOI":"10.1145\/3534678.3539391"},{"key":"2472_CR184","unstructured":"Yang S, Dong Y, Ward R, Dhillon IS, Sanghavi S, Lei Q (2022b) Sample efficiency of data augmentation consistency regularization. arXiv preprint arXiv:2202.12230"},{"key":"2472_CR185","unstructured":"Yang S, Xiao W, Zhang M, Guo S, Zhao J, Shen F (2022c) Image data augmentation for deep learning: A survey. arXiv preprint arXiv:2204.08610"},{"key":"2472_CR186","doi-asserted-by":"crossref","unstructured":"Yang X, Wang X (2023) Diffusion model as representation learner. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 18938\u201318949","DOI":"10.1109\/ICCV51070.2023.01736"},{"key":"2472_CR187","doi-asserted-by":"crossref","unstructured":"Yang X, Ye J, Wang X (2022d) Factorizing knowledge in neural networks. In: European Conference on Computer Vision, Springer, pp 73\u201391","DOI":"10.1007\/978-3-031-19830-4_5"},{"key":"2472_CR188","first-page":"25739","volume":"35","author":"X Yang","year":"2022","unstructured":"Yang, X., Zhou, D., Liu, S., Ye, J., & Wang, X. (2022). Deep model reassembly. Advances in neural information processing systems, 35, 25739\u201325753.","journal-title":"Advances in neural information processing systems"},{"key":"2472_CR189","unstructured":"Yarats D, Kostrikov I, Fergus R (2020) Image augmentation is all you need: Regularizing deep reinforcement learning from pixels. In: International Conference on Learning Representations"},{"key":"2472_CR190","unstructured":"Yarats D, Fergus R, Lazaric A, Pinto L (2021a) Mastering visual continuous control: Improved data-augmented reinforcement learning. In: International Conference on Learning Representations"},{"key":"2472_CR191","unstructured":"Yarats D, Fergus R, Lazaric A, Pinto L (2021b) Reinforcement learning with prototypical representations. In: International Conference on Machine Learning, PMLR"},{"key":"2472_CR192","doi-asserted-by":"crossref","unstructured":"Yarats D, Zhang A, Kostrikov I, Amos B, Pineau J, Fergus R (2021c) Improving sample efficiency in model-free reinforcement learning from images. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol\u00a035","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"2472_CR193","doi-asserted-by":"crossref","unstructured":"You B, Arenz O, Chen Y, Peters J (2022) Integrating contrastive learning with dynamic models for reinforcement learning from images. Neurocomputing","DOI":"10.1016\/j.neucom.2021.12.094"},{"key":"2472_CR194","unstructured":"Yu T, Lan C, Zeng W, Feng M, Zhang Z, Chen Z (2021) Playvirtual: Augmenting cycle-consistent virtual trajectories for reinforcement learning. Advances in Neural Information Processing Systems 34"},{"key":"2472_CR195","unstructured":"Yu T, Zhang Z, Lan C, Chen Z, Lu Y (2022) Mask-based latent reconstruction for reinforcement learning. arXiv preprint arXiv:2201.12096"},{"key":"2472_CR196","doi-asserted-by":"crossref","unstructured":"Yu T, Xiao T, Stone A, Tompson J, Brohan A, Wang S, Singh J, Tan C, Peralta J, Ichter B, et\u00a0al. (2023) Scaling robot learning with semantically imagined experience. arXiv preprint arXiv:2302.11550","DOI":"10.15607\/RSS.2023.XIX.027"},{"key":"2472_CR197","doi-asserted-by":"crossref","unstructured":"Yu Y (2018) Towards sample efficient reinforcement learning. In: IJCAI, pp 5739\u20135743","DOI":"10.24963\/ijcai.2018\/820"},{"key":"2472_CR198","doi-asserted-by":"crossref","unstructured":"Yuan Z, Ma G, Mu Y, Xia B, Yuan B, Wang X, Luo P, Xu H (2022a) Don\u2019t touch what matters: Task-aware lipschitz data augmentationfor visual reinforcement learning. arXiv preprint arXiv:2202.09982","DOI":"10.24963\/ijcai.2022\/514"},{"key":"2472_CR199","unstructured":"Yuan Z, Xue Z, Yuan B, Wang X, Wu Y, Gao Y, Xu H (2022b) Pre-trained image encoder for generalizable visual reinforcement learning. In: First Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward at ICML 2022"},{"key":"2472_CR200","unstructured":"Yuan Z, Wei T, Cheng S, Zhang G, Chen Y, Xu H (2024) Learning to manipulate anywhere: A visual generalizable framework for reinforcement learning. arXiv preprint arXiv:2407.15815"},{"key":"2472_CR201","unstructured":"Yue Y, Kang B, Ma X, Xu Z, Huang G, Yan S (2022) Boosting offline reinforcement learning via data rebalancing. arXiv preprint arXiv:2210.09241"},{"key":"2472_CR202","doi-asserted-by":"crossref","unstructured":"Yun S, Han D, Oh SJ, Chun S, Choe J, Yoo Y (2019) Cutmix: Regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6023\u20136032","DOI":"10.1109\/ICCV.2019.00612"},{"key":"2472_CR203","unstructured":"Zhang A, Wu Y, Pineau J (2018a) Natural environment benchmarks for reinforcement learning. arXiv preprint arXiv:1811.06032"},{"key":"2472_CR204","unstructured":"Zhang A, Lyle C, Sodhani S, Filos A, Kwiatkowska M, Pineau J, Gal Y, Precup D (2020a) Invariant causal prediction for block mdps. In: International Conference on Machine Learning, PMLR, pp 11214\u201311224"},{"key":"2472_CR205","unstructured":"Zhang A, McAllister R, Calandra R, Gal Y, Levine S (2020b) Learning invariant representations for reinforcement learning without reconstruction. arXiv preprint arXiv:2006.10742"},{"key":"2472_CR206","unstructured":"Zhang C, Vinyals O, Munos R, Bengio S (2018b) A study on overfitting in deep reinforcement learning. arXiv preprint arXiv:1804.06893"},{"key":"2472_CR207","unstructured":"Zhang H, Cisse M, Dauphin YN, Lopez-Paz D (2017) mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412"},{"key":"2472_CR208","doi-asserted-by":"crossref","unstructured":"Zhang J, Ma K (2022) Rethinking the augmentation module in contrastive learning: Learning hierarchical augmentation invariance with expanded views. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR52688.2022.01615"},{"key":"2472_CR209","unstructured":"Zhang L, Deng Z, Kawaguchi K, Ghorbani A, Zou J (2020c) How does mixup help with robustness and generalization? arXiv preprint arXiv:2010.04819"},{"key":"2472_CR210","doi-asserted-by":"crossref","unstructured":"Zhang R, Torabi F, Guan L, Ballard DH, Stone P (2019) Leveraging human guidance for deep reinforcement learning tasks. arXiv preprint arXiv:1909.09906","DOI":"10.24963\/ijcai.2019\/884"},{"key":"2472_CR211","unstructured":"Zheng C, Wu G, Li C (2024) Toward understanding generative data augmentation. Advances in Neural Information Processing Systems 36"},{"key":"2472_CR212","unstructured":"Zhong Z, Zheng L, Kang G, Li S, Yang Y (2017) Random erasing data augmentation. arXiv preprint arXiv:1708.04896"},{"key":"2472_CR213","unstructured":"Zhou K, Yang Y, Qiao Y, Xiang T (2020) Domain generalization with mixstyle. In: International Conference on Learning Representations"},{"key":"2472_CR214","doi-asserted-by":"crossref","unstructured":"Zhu J, Xia Y, Wu L, Deng J, Zhou W, Qin T, Liu TY, Li H (2022) Masked contrastive representation learning for reinforcement learning. IEEE Transactions on Pattern Analysis and Machine Intelligence","DOI":"10.1109\/TPAMI.2022.3176413"},{"key":"2472_CR215","unstructured":"Zhu Y, Wong J, Mandlekar A, Mart\u00edn-Mart\u00edn R (2020) robosuite: A modular simulation framework and benchmark for robot learning. arXiv preprint arXiv:2009.12293"},{"key":"2472_CR216","unstructured":"Zhu Z, Zhao H, He H, Zhong Y, Zhang S, Yu Y, Zhang W (2023) Diffusion models for reinforcement learning: A survey. arXiv preprint arXiv:2311.01223"},{"key":"2472_CR217","unstructured":"Zou D, Cao Y, Li Y, Gu Q (2023) The benefits of mixup for feature learning. In: International Conference on Machine Learning, PMLR, pp 43423\u201343479"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02472-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02472-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02472-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T08:49:43Z","timestamp":1760086183000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02472-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,28]]},"references-count":217,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["2472"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02472-w","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,28]]},"assertion":[{"value":"1 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}