A Survey on Reinforcement Learning Methods in Character Animation

TL;DR

This survey reviews modern Deep Reinforcement Learning techniques and their applications in character animation, covering skeletal control, navigation, and practical training frameworks for virtual characters.

Contribution

It provides a comprehensive overview of DRL methods applied to character animation and discusses practical training frameworks and applications.

Findings

DRL methods enable realistic character control and navigation.

Various frameworks facilitate training DRL agents for animation tasks.

Survey highlights current challenges and future directions in the field.

Abstract

Reinforcement Learning is an area of Machine Learning focused on how agents can be trained to make sequential decisions, and achieve a particular goal within an arbitrary environment. While learning, they repeatedly take actions based on their observation of the environment, and receive appropriate rewards which define the objective. This experience is then used to progressively improve the policy controlling the agent's behavior, typically represented by a neural network. This trained module can then be reused for similar problems, which makes this approach promising for the animation of autonomous, yet reactive characters in simulators, video games or virtual reality environments. This paper surveys the modern Deep Reinforcement Learning methods and discusses their possible applications in Character Animation, from skeletal control of a single, physically-based character to navigation controllers for individual agents and virtual crowds. It also describes the practical side of training DRL systems, comparing the different frameworks available to build such agents.