{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T09:43:19Z","timestamp":1743068599473,"version":"3.40.3"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031703515"},{"type":"electronic","value":"9783031703522"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-70352-2_8","type":"book-chapter","created":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T00:01:55Z","timestamp":1724976115000},"page":"127-142","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ApmNet: Toward Generalizable Visual Continuous Control with\u00a0Pre-trained Image Models"],"prefix":"10.1007","author":[{"given":"Haitao","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hejun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,22]]},"reference":[{"unstructured":"Ball, P.J., Smith, L., Kostrikov, I., Levine, S.: Efficient online reinforcement learning with offline data. arXiv preprint arXiv:2302.02948 (2023)","key":"8_CR1"},{"unstructured":"Banino, A., Badia, A.P., Walker, J., Scholtes, T., Mitrovic, J., Blundell, C.: Coberl: contrastive bert for reinforcement learning. arXiv preprint arXiv:2107.05431 (2021)","key":"8_CR2"},{"doi-asserted-by":"crossref","unstructured":"Bellman, R.: A Markovian decision process. J. Math. Mech. 679\u2013684 (1957)","key":"8_CR3","DOI":"10.1512\/iumj.1957.6.56038"},{"unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.E.: A simple framework for contrastive learning of visual representations. ArXiv arxiv:2002.05709 (2020)","key":"8_CR4"},{"unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)","key":"8_CR5"},{"unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)","key":"8_CR6"},{"unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)","key":"8_CR7"},{"unstructured":"Du, Y., et al.: Guiding pretraining in reinforcement learning with large language models. arXiv preprint arXiv:2302.06692 (2023)","key":"8_CR8"},{"doi-asserted-by":"crossref","unstructured":"Ebert, F., et al.: Bridge data: boosting generalization of robotic skills with cross-domain datasets. arXiv preprint arXiv:2109.13396 (2021)","key":"8_CR9","DOI":"10.15607\/RSS.2022.XVIII.063"},{"unstructured":"Goodfellow, I.J., et al.: Generative adversarial networks. CoRR arxiv:1406.2661 (2014)","key":"8_CR10"},{"unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. ArXiv arxiv:1801.01290 (2018)","key":"8_CR11"},{"unstructured":"Hafner, D., Lillicrap, T., Norouzi, M., Ba, J.: Mastering atari with discrete world models. arXiv preprint arXiv:2010.02193 (2020)","key":"8_CR12"},{"unstructured":"Hafner, D., Pasukonis, J., Ba, J., Lillicrap, T.: Mastering diverse domains through world models. arXiv preprint arXiv:2301.04104 (2023)","key":"8_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 (2020)","key":"8_CR14","DOI":"10.1109\/ICRA48506.2021.9561103"},{"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)","key":"8_CR15","DOI":"10.1109\/CVPR52688.2022.01553"},{"doi-asserted-by":"crossref","unstructured":"He, K.,\u00a0Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2015)","key":"8_CR16","DOI":"10.1109\/CVPR.2016.90"},{"unstructured":"Huang, X., Zhou, H., Yao, K., Han, K.: Froster: frozen clip is a strong teacher for open-vocabulary action recognition. ArXiv arxiv:2402.03241 (2024)","key":"8_CR17"},{"doi-asserted-by":"crossref","unstructured":"Khandelwal, A., Weihs, L., Mottaghi, R., Kembhavi, A.: Simple but effective: clip embeddings for embodied AI. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14829\u201314838 (2022)","key":"8_CR18","DOI":"10.1109\/CVPR52688.2022.01441"},{"unstructured":"Kostrikov, I., Yarats, D., Fergus, R.: Image augmentation is all you need: regularizing deep reinforcement learning from pixels. ArXiv arxiv:2004.13649 (2020)","key":"8_CR19"},{"unstructured":"Laskin, M., Lee, K., Stooke, A., Pinto, L., Abbeel, P., Srinivas, A.: Reinforcement learning with augmented data. ArXiv arxiv:2004.14990 (2020)","key":"8_CR20"},{"doi-asserted-by":"crossref","unstructured":"Lin, X., So, J., Mahalingam, S., Liu, F., Abbeel, P.: Spawnnet: learning generalizable visuomotor skills from pre-trained networks. ArXiv arxiv:2307.03567 (2023)","key":"8_CR21","DOI":"10.1109\/ICRA57147.2024.10610356"},{"unstructured":"Raileanu, R., Goldstein, M., Yarats, D., Kostrikov, I., Fergus, R.: Automatic data augmentation for generalization in reinforcement learning. In: Neural Information Processing Systems (2021)","key":"8_CR22"},{"doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Conference on Computer Vision and Pattern Recognition 2022, pp. 10674\u201310685 (2022)","key":"8_CR23","DOI":"10.1109\/CVPR52688.2022.01042"},{"unstructured":"Schwarzer, M., Anand, A., Goel, R., Hjelm, R.D., Courville, A.C., Bachman, P.: Data-efficient reinforcement learning with momentum predictive representations. ArXiv arxiv:2007.05929 (2020)","key":"8_CR24"},{"unstructured":"Seo, Y., et al.: Masked world models for visual control. In: Conference on Robot Learning, pp. 1332\u20131344 (2023)","key":"8_CR25"},{"unstructured":"Seo, Y., Lee, K., James, S.L., Abbeel, P.: Reinforcement learning with action-free pre-training from videos. In: International Conference on Machine Learning, pp. 19561\u201319579 (2022)","key":"8_CR26"},{"unstructured":"Shah, R., Kumar, V.: Rrl: resnet as representation for reinforcement learning. ArXiv arxiv:2107.03380 (2021)","key":"8_CR27"},{"unstructured":"Shridhar, M., Manuelli, L., Fox, D.: Cliport: what and where pathways for robotic manipulation. In: Conference on Robot Learning, pp. 894\u2013906. PMLR (2022)","key":"8_CR28"},{"unstructured":"Srinivas, A., Laskin, M., Abbeel, P.: Curl: contrastive unsupervised representations for reinforcement learning. In: International Conference on Machine Learning (2020)","key":"8_CR29"},{"unstructured":"Stooke, A., Lee, K.,\u00a0Abbeel, P., Laskin, M.: Decoupling representation learning from reinforcement learning. ArXiv arxiv:2009.08319 (2020)","key":"8_CR30"},{"unstructured":"Tassa, Y., et al.: Deepmind control suite. ArXiv arxiv:1801.00690 (2018)","key":"8_CR31"},{"unstructured":"Van\u00a0der Maaten, L., Hinton, G.: Visualizing data using t-sne. J. Mach. Learn. Res. 9(11) (2008)","key":"8_CR32"},{"unstructured":"Wang, C., Luo, X., Ross, K.W., Li, D.: Vrl3: a data-driven framework for visual deep reinforcement learning. ArXiv arxiv:2202.10324 (2022)","key":"8_CR33"},{"doi-asserted-by":"crossref","unstructured":"Wang, X., Lian, L., Yu, S.X.: Unsupervised visual attention and invariance for reinforcement learning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6673\u20136683 (2021)","key":"8_CR34","DOI":"10.1109\/CVPR46437.2021.00661"},{"unstructured":"Xiao, T., Radosavovic, I., Darrell, T., Malik, J.: Masked visual pre-training for motor control. arXiv preprint arXiv:2203.06173 (2022)","key":"8_CR35"},{"unstructured":"Xu, H., Ding, S., Zhang, X., Xiong, H., Tian, Q.: Masked autoencoders are robust data augmentors. ArXiv arxiv:2206.04846 (2022)","key":"8_CR36"},{"unstructured":"Yang, T., Zhu, Y., Xie, Y., Zhang, A., Chen, C., Li, M.: Aim: adapting image models for efficient video action recognition. ArXiv arxiv:2302.03024 (2023)","key":"8_CR37"},{"unstructured":"Yarats, D., Fergus, R., Lazaric, A., Pinto, L.: Mastering visual continuous control: improved data-augmented reinforcement learning. ArXiv arxiv:2107.09645 (2021)","key":"8_CR38"},{"unstructured":"Yarats, D., Fergus, R., Lazaric, A., Pinto, L.: Reinforcement learning with prototypical representations. In: International Conference on Machine Learning (2021)","key":"8_CR39"},{"doi-asserted-by":"crossref","unstructured":"Yen-Chen, L., Zeng, A., Song, S., Isola, P., Lin, T.Y.: Learning to see before learning to act: Visual pre-training for manipulation. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 7286\u20137293. IEEE (2020)","key":"8_CR40","DOI":"10.1109\/ICRA40945.2020.9197331"},{"unstructured":"Yu, T., et al.: Meta-world: a benchmark and evaluation for multi-task and meta reinforcement learning. ArXiv arxiv:1910.10897 (2019)","key":"8_CR41"},{"key":"8_CR42","first-page":"13022","volume":"35","author":"Z Yuan","year":"2022","unstructured":"Yuan, Z., et al.: 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."}],"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\/978-3-031-70352-2_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T13:51:20Z","timestamp":1732715480000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70352-2_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031703515","9783031703522"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70352-2_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"22 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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":"Vilnius","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","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 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}