Exploring the Effectiveness of GAN-based Approach and Reinforcement Learning in Character Boxing Task
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Son, Seoyoung | - |
dc.contributor.author | Kwon, Taesoo | - |
dc.date.accessioned | 2023-09-18T06:20:24Z | - |
dc.date.available | 2023-09-18T06:20:24Z | - |
dc.date.created | 2023-09-11 | - |
dc.date.issued | 2023-09 | - |
dc.identifier.issn | 1975-7883 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/190541 | - |
dc.description.abstract | For decades, creating a desired locomotive motion in a goal-oriented manner has been a challenge in character animation. Datadriven methods using generative models have demonstrated efficient ways of predicting long sequences of motions without the need for explicit conditioning. While these methods produce high-quality long-term motions, they can be limited when it comes to synthesizing motion for challenging novel scenarios, such as punching a random target. A state-of-the-art solution to overcome this limitation is by using a GAN Discriminator to imitate motion data clips and incorporating reinforcement learning to compose goaloriented motions. In this paper, our research aims to create characters performing combat sports such as boxing, using a novel reward design in conjunction with existing GAN-based approaches. We experimentally demonstrate that both the Adversarial Motion Prior [3] and Adversarial Skill Embeddings [4] methods are capable of generating viable motions for a character punching a random target, even in the absence of mocap data that specifically captures the transition between punching and locomotion. Also, with a single learned policy, multiple task controllers can be constructed through the TimeChamber framework. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | (사)한국컴퓨터그래픽스학회 | - |
dc.title | Exploring the Effectiveness of GAN-based Approach and Reinforcement Learning in Character Boxing Task | - |
dc.title.alternative | 캐릭터 복싱 과제에서 GAN 기반 접근법과 강화학습의 효과성 탐구 | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kwon, Taesoo | - |
dc.identifier.doi | 10.15701/kcgs.2023.29.4.7 | - |
dc.identifier.bibliographicCitation | 한국컴퓨터그래픽스학회논문지, v.29, no.4, pp.7 - 16 | - |
dc.relation.isPartOf | 한국컴퓨터그래픽스학회논문지 | - |
dc.citation.title | 한국컴퓨터그래픽스학회논문지 | - |
dc.citation.volume | 29 | - |
dc.citation.number | 4 | - |
dc.citation.startPage | 7 | - |
dc.citation.endPage | 16 | - |
dc.type.rims | ART | - |
dc.identifier.kciid | ART002993662 | - |
dc.description.journalClass | 2 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | kci | - |
dc.subject.keywordAuthor | Character Animation | - |
dc.subject.keywordAuthor | Physics-based Simulation | - |
dc.subject.keywordAuthor | Reinforcement Learning | - |
dc.subject.keywordAuthor | GAN | - |
dc.subject.keywordAuthor | 캐릭터 애니메이션 | - |
dc.subject.keywordAuthor | 물리기반 시뮬레이션 | - |
dc.subject.keywordAuthor | 강화학습 | - |
dc.subject.keywordAuthor | GAN | - |
dc.identifier.url | https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART002993662 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
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.