English

Utilizing Motion Matching with Deep Reinforcement Learning for Target Location Tasks

Graphics 2024-03-26 v1

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.

Keywords

Cite

@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}
}

Comments

Eurographics 2024 Short Papers

R2 v1 2026-06-28T15:31:10.164Z