DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jain, Ayush | ko |
dc.contributor.author | Kosaka, Norio | ko |
dc.contributor.author | Kim, Kyung-Min | ko |
dc.contributor.author | Lim, Joseph Jaewhan | ko |
dc.date.accessioned | 2023-09-15T05:00:26Z | - |
dc.date.available | 2023-09-15T05:00:26Z | - |
dc.date.created | 2023-09-15 | - |
dc.date.issued | 2022-04 | - |
dc.identifier.citation | 10th International Conference on Learning Representations, ICLR 2022 | - |
dc.identifier.uri | http://hdl.handle.net/10203/312664 | - |
dc.description.abstract | Intelligent agents can solve tasks in various ways depending on their available set of actions. However, conventional reinforcement learning (RL) assumes a fixed action set. This work asserts that tasks with varying action sets require reasoning of the relations between the available actions. For instance, taking a nail-action in a repair task is meaningful only if a hammer-action is also available. To learn and utilize such action relations, we propose a novel policy architecture consisting of a graph attention network over the available actions. We show that our model makes informed action decisions by correctly attending to other related actions in both value-based and policy-based RL. Consequently, it outperforms non-relational architectures on applications where the action space often varies, such as recommender systems and physical reasoning with tools and skills. | - |
dc.language | English | - |
dc.publisher | International Conference on Learning Representations, ICLR | - |
dc.title | KNOW YOUR ACTION SET: LEARNING ACTION RELATIONS FOR REINFORCEMENT LEARNING | - |
dc.type | Conference | - |
dc.identifier.scopusid | 2-s2.0-85143674558 | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | 10th International Conference on Learning Representations, ICLR 2022 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Virtual | - |
dc.contributor.localauthor | Lim, Joseph Jaewhan | - |
dc.contributor.nonIdAuthor | Jain, Ayush | - |
dc.contributor.nonIdAuthor | Kosaka, Norio | - |
dc.contributor.nonIdAuthor | Kim, Kyung-Min | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.