Exploring the Effectiveness of GAN-based Approach and Reinforcement Learning in Character Boxing Task캐릭터 복싱 과제에서 GAN 기반 접근법과 강화학습의 효과성 탐구
- Other Titles
- 캐릭터 복싱 과제에서 GAN 기반 접근법과 강화학습의 효과성 탐구
- Authors
- Son, Seoyoung; Kwon, Taesoo
- Issue Date
- Sep-2023
- Publisher
- (사)한국컴퓨터그래픽스학회
- Keywords
- Character Animation; Physics-based Simulation; Reinforcement Learning; GAN; 캐릭터 애니메이션; 물리기반 시뮬레이션; 강화학습; GAN
- Citation
- 한국컴퓨터그래픽스학회논문지, v.29, no.4, pp.7 - 16
- Indexed
- KCI
- Journal Title
- 한국컴퓨터그래픽스학회논문지
- Volume
- 29
- Number
- 4
- Start Page
- 7
- End Page
- 16
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/190541
- DOI
- 10.15701/kcgs.2023.29.4.7
- ISSN
- 1975-7883
- 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.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 컴퓨터소프트웨어학부 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/190541)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.