DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Kimin | ko |
dc.contributor.author | SEO, YOUNGGYO | ko |
dc.contributor.author | Lee, Seunghyun | ko |
dc.contributor.author | Shin, Jinwoo | ko |
dc.date.accessioned | 2020-12-15T06:10:17Z | - |
dc.date.available | 2020-12-15T06:10:17Z | - |
dc.date.created | 2020-12-02 | - |
dc.date.created | 2020-12-02 | - |
dc.date.created | 2020-12-02 | - |
dc.date.created | 2020-12-02 | - |
dc.date.issued | 2020-07-15 | - |
dc.identifier.citation | Thirty-seventh International Conference on Machine Learning, ICML 2020, pp.5713 - 5722 | - |
dc.identifier.issn | 2640-3498 | - |
dc.identifier.uri | http://hdl.handle.net/10203/278491 | - |
dc.description.abstract | Model-based reinforcement learning (RL) enjoys several benefits, such as data-efficiency and planning, by learning a model of the environment's dynamics. However, learning a global model that can generalize across different dynamics is a challenging task. To tackle this problem, we decompose the task of learning a global dynamics model into two stages: (a) learning a context latent vector that captures the local dynamics, then (b) predicting the next state conditioned on it. In order to encode dynamics-specific information into the context latent vector, we introduce a novel loss function that encourages the context latent vector to be useful for predicting both forward and backward dynamics. The proposed method achieves superior generalization ability across various simulated robotics and control tasks, compared to existing RL schemes. | - |
dc.language | English | - |
dc.publisher | International Conference on Machine Learning | - |
dc.title | Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning | - |
dc.type | Conference | - |
dc.identifier.wosid | 000683178505082 | - |
dc.identifier.scopusid | 2-s2.0-85105585026 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 5713 | - |
dc.citation.endingpage | 5722 | - |
dc.citation.publicationname | Thirty-seventh International Conference on Machine Learning, ICML 2020 | - |
dc.identifier.conferencecountry | AU | - |
dc.identifier.conferencelocation | Virtual | - |
dc.contributor.localauthor | Lee, Kimin | - |
dc.contributor.localauthor | Shin, Jinwoo | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.