GRAPHICS

REINFORCEMENT LEARNING

Control Strategies for Physically Simulated Characters Performing Two-player Competitive Sports

August 9, 2021

Abstract

In two-player competitive sports, such as boxing and fencing, athletes often demonstrate efficient and tactical movements during a competition. In this paper, we develop a learning framework that generates control policies for physically simulated athletes who have many degrees-of-freedom. Our framework uses a two step-approach, learning basic skills and learning bout-level strategies, with deep reinforcement learning, which is inspired by the way that people learn competitive sports. We develop a policy model based on an encoder-decoder structure that incorporates an autoregressive latent variable, and a mixture-of-experts decoder. To show the effectiveness of our framework, we implemented two competitive sports, boxing and fencing, and demonstrate control policies learned by our framework that can generate both tactical and natural-looking behaviors. We also evaluate the control policies with comparisons to other learning configurations and with ablation studies.

Something Went Wrong
We're having trouble playing this video.

Something Went Wrong
We're having trouble playing this video.

Download the Paper

AUTHORS

Written by

Jungdam Won

Deepak Gopinath

Jessica Hodgins

Publisher

SIGGRAPH 2021

Research Topics

Reinforcement Learning

Graphics

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.