DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Kee-Eung | - |
dc.contributor.advisor | 김기응 | - |
dc.contributor.author | Hong, Sunghoon | - |
dc.date.accessioned | 2023-06-22T19:31:10Z | - |
dc.date.available | 2023-06-22T19:31:10Z | - |
dc.date.issued | 2022 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=997688&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/308175 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 김재철AI대학원, 2022.2,[iii, 21 p. :] | - |
dc.description.abstract | Modular Reinforcement Learning, where the agent is assumed to be morphologically structured as a graph, for example composed of limbs and joints, aims to learn a policy that is transferable to a structurally similar but different agent. Compared to traditional Multi-Task Reinforcement Learning, this promising approach allows us to cope with inhomogeneous tasks where the state and action space dimensions differ across tasks. Graph Neural Networks are a natural model for representing the pertinent policies, but a recent work has shown that their multi-hop message passing mechanism is not ideal for conveying important information to other modules and thus a transformer model without morphological information was proposed. In this work, we argue that the morphological information is still very useful and propose a transformer policy model that effectively encodes such information. Specifically, we encode the morphological information in terms of the traversal-based positional embedding and the graph-based relational embedding. We empirically show that the morphological information is crucial for modular reinforcement learning, substantially outperforming prior state-of-the-art methods on multi-task learning as well as transfer learning settings with different state and action space dimensions. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.title | Structure-aware transformer policy for inhomogeneous multi-task reinforcement learning | - |
dc.title.alternative | 불균일 다중 작업 강화학습을 위한 구조 인식 트랜스포머 정책 연구 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :김재철AI대학원, | - |
dc.contributor.alternativeauthor | 홍성훈 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.