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.
@article{arxiv.2403.15902,
title = {Utilizing Motion Matching with Deep Reinforcement Learning for Target Location Tasks},
author = {Jeongmin Lee and Taesoo Kwon and Hyunju Shin and Yoonsang Lee},
journal= {arXiv preprint arXiv:2403.15902},
year = {2024}
}