Utilizing Motion Matching with Deep Reinforcement Learning for Target Location Tasks
No Thumbnail Available
Date
2024
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
We present an approach using deep reinforcement learning (DRL) to directly generate motion matching queries for longterm tasks, particularly targeting the reaching of specific locations. By integrating motion matching and DRL, our method demonstrates the rapid learning of policies for target location tasks within minutes on a standard desktop, employing a simple reward design. Additionally, we propose a unique hit reward and obstacle curriculum scheme to enhance policy learning in environments with moving obstacles.
Description
CCS Concepts: Computing methodologies → Motion processing; Motion path planning
@inproceedings{10.2312:egs.20241020,
booktitle = {Eurographics 2024 - Short Papers},
editor = {Hu, Ruizhen and Charalambous, Panayiotis},
title = {{Utilizing Motion Matching with Deep Reinforcement Learning for Target Location Tasks}},
author = {Lee, Jeongmin and Kwon, Taesoo and Shin, Hyunju and Lee, Yoonsang},
year = {2024},
publisher = {The Eurographics Association},
ISSN = {1017-4656},
ISBN = {978-3-03868-237-0},
DOI = {10.2312/egs.20241020}
}