{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T23:00:54Z","timestamp":1760482854222},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7]]},"abstract":"<jats:p>Vision-based reinforcement learning requires efficient and robust representations of image-based observations, especially when the images contain distracting (task-irrelevant) elements such as shadows, clouds, and light. It becomes more important if those distractions are not exposed during training. We design a Self-Predictive Dynamics (SPD) method to extract task-relevant features efficiently, even in unseen observations after training. SPD uses weak and strong augmentations in parallel, and learns representations by predicting inverse and forward transitions across the two-way augmented versions. In a set of MuJoCo visual control tasks and an autonomous driving task (CARLA), SPD outperforms previous studies in complex observations, and significantly improves the generalization performance for unseen observations. Our code is available at https:\/\/github.com\/unigary\/SPD.<\/jats:p>","DOI":"10.24963\/ijcai.2022\/437","type":"proceedings-article","created":{"date-parts":[[2022,7,16]],"date-time":"2022-07-16T02:55:56Z","timestamp":1657940156000},"page":"3150-3156","source":"Crossref","is-referenced-by-count":3,"title":["Self-Predictive Dynamics for Generalization of Vision-based Reinforcement Learning"],"prefix":"10.24963","author":[{"given":"Kyungsoo","family":"Kim","sequence":"first","affiliation":[{"name":"Sungkyunkwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeongsoo","family":"Ha","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusung","family":"Kim","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"number":"31","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2022","name":"Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}","start":{"date-parts":[[2022,7,23]]},"theme":"Artificial Intelligence","location":"Vienna, Austria","end":{"date-parts":[[2022,7,29]]}},"container-title":["Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T11:09:43Z","timestamp":1658142583000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2022\/437"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2022\/437","relation":{},"subject":[],"published":{"date-parts":[[2022,7]]}}}