Reinforcement Learning Approaches for Locomotion Planning in Interactive Applications

Locomotion is one of the most important capabilities for virtual human agents in interactive applications, because it allows them to navigate their environment. Locomotion controllers in interactive applications typically work by blending and concatenating clips of keyframe or motion capture motion that represent individual locomotion actions (e.g. walk cycles), to generate sequences of natural-looking, task-appropriate character motion. The key challenge of locomotion implementation is planning i.e. choosing an optimal sequence of locomotion actions that achieves a high-level navigation goal. In recent years researchers have successfully applied reinforcement learning to this problem. In this paper we give an overview of these efforts, and demonstrate our own application of reinforcement learning to a simple navigation task.