Utilizing Motion Matching with Deep Reinforcement Learning for Target Location Tasks

Jeongmin Lee, Taesoo Kwon, Hyunju Shin, Yoonsang Lee
Eurographics 2024 Short Papers

Abstract

We present an approach using deep reinforcement learning (DRL) to directly generate motion matching queries for long-term 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.

Paper

Publisher: page, paper
arXiv: page, paper

Video

Slides

Eurographics 2024 presentation slides: pdf (1.5MB), pptx (289.5MB)