Distributional Deep Reinforcement Learning with a Mixture of Gaussians
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Choi, Yunho | - |
dc.contributor.author | Lee, Kyungjae | - |
dc.contributor.author | Oh, Songhwai | - |
dc.date.accessioned | 2022-11-28T01:57:58Z | - |
dc.date.available | 2022-11-28T01:57:58Z | - |
dc.date.issued | 2019-05 | - |
dc.identifier.issn | 1050-4729 | - |
dc.identifier.issn | 2577-087X | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/59369 | - |
dc.description.abstract | In this paper, we propose a novel distributional reinforcement learning (RL) method which models the distribution of the sum of rewards using a mixture density network. Recently, it has been shown that modeling the randomness of the return distribution leads to better performance in Atari games and control tasks. Despite the success of the prior work, it has limitations which come from the use of a discrete distribution. First, it needs a projection step and softmax parametrization for the distribution, since it minimizes the KL divergence loss. Secondly, its performance depends on discretization hyperparameters such as the number of atoms and bounds of the support which require domain knowledge. We mitigate these problems with the proposed parameterization, a mixture of Gaussians. Furthermore, we propose a new distance metric called the Jensen-Tsallis distance, which allows the computation of the distance between two mixtures of Gaussians in a closed form. We have conducted various experiments to validate the proposed method, including Atari games and autonomous vehicle driving. | - |
dc.format.extent | 7 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | IEEE | - |
dc.title | Distributional Deep Reinforcement Learning with a Mixture of Gaussians | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/ICRA.2019.8793505 | - |
dc.identifier.bibliographicCitation | 2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), pp 9791 - 9797 | - |
dc.description.isOpenAccess | N | - |
dc.identifier.wosid | 000494942307029 | - |
dc.identifier.scopusid | 2-s2.0-85071499524 | - |
dc.citation.endPage | 9797 | - |
dc.citation.startPage | 9791 | - |
dc.citation.title | 2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA) | - |
dc.type.docType | Proceedings Paper | - |
dc.publisher.location | 미국 | - |
dc.relation.journalResearchArea | Automation & Control Systems | - |
dc.relation.journalResearchArea | Robotics | - |
dc.relation.journalWebOfScienceCategory | Automation & Control Systems | - |
dc.relation.journalWebOfScienceCategory | Robotics | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
84, Heukseok-ro, Dongjak-gu, Seoul, Republic of Korea (06974)02-820-6194
COPYRIGHT 2019 Chung-Ang University All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.