DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 신진우 | - |
dc.contributor.author | Seo, Younggyo | - |
dc.contributor.author | 서영교 | - |
dc.date.accessioned | 2024-07-26T19:30:25Z | - |
dc.date.available | 2024-07-26T19:30:25Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1046585&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/320815 | - |
dc.description | 학위논문(박사) - 한국과학기술원 : 김재철AI대학원, 2023.8,[iii, 57 p. :] | - |
dc.description.abstract | Model-based approaches, which predict future consequences of potential actions and make decisions based on these predictions, hold substantial potential for efficiently learning to achieve target tasks. The capability of model-based agents relies on the accuracy of planning, but learning a world model with accurate planning capability is often difficult and costly. This dissertation argues that improving the representation learning from high-dimensional visual observations would enable us to efficiently learn world models and endow agents with the planning capability. First, we show how pre-training representations from diverse, action-free videos can accelerate world model learning on unseen environments, thereby reducing the number of samples required for solving the newly encountered tasks. Second, we present a new model-based framework that decouples visual representation learning and dynamics learning, along with a self-supervised learning approach that adapts a recently-developed masked autoencoding approach to be better suited for visual control. Finally, we extend our framework to a practical robot learning scenario that utilizes multiple cameras, by introducing a novel representation learning method that reconstructs masked viewpoints to learn cross-view information. The approaches we present in this thesis demonstrate strong empirical results in both simulated and real-world benchmarks, highlighting the importance of learning succinct visual representations for world model learning. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 모델기반 강화학습▼a시각 제어▼a표현 학습▼a마스킹 기반 오토인코더▼a비디오 예측▼a사전학습 | - |
dc.subject | Model-based reinforcement learning▼aVisual control▼aRepresentation learning▼aMasked autoencoding▼aVideo prediction▼aPre-training | - |
dc.title | Representation learning for visual control with world models | - |
dc.title.alternative | 세계 모델을 이용한 시각 제어를 위한 표현 학습 | - |
dc.type | Thesis(Ph.D) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :김재철AI대학원, | - |
dc.contributor.alternativeauthor | Shin, Jinwoo | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.