[2G5-OS-21e] 世界モデルと知能

[2G5-OS-21e-05] Animation Guided Reinforcement Learning for Generating Physically Plausible Complex Behavior

〇Hiroki Oba¹, Naruya Kondo², Yusuke Iwasawa¹, Yutaka Matsuo¹ (1. The University of Tokyo, 2. University of Tsukuba)

Keywords:generative model, reinforcement learning

The acquisition of complex human motions in a simulator space is expected to be significant in various scenes such as games and 3DCG animation. One such method is reinforcement learning by using motion-captured human motions as references, but acquiring reference motions is expensive because it requires equipment and actors. However, the cost is high because it requires equipment and actors to acquire reference motions. Against this background, this study investigates the applicability and problems of using the Motion Diffusion Model, a current SOTA model, for generating reference motions.