Reinforcement Learning Agents for Ubisoft's Roller Champions

TL;DR

This paper demonstrates that reinforcement learning can effectively create AI agents for complex modern video games, specifically Ubisoft's Roller Champions, with rapid training and adaptable strategies.

Contribution

The paper introduces a reinforcement learning system tailored for Roller Champions, capable of quick training and versatile adaptation across multiple game modes, showcasing practical application in a non-trivial game.

Findings

AI agents develop sophisticated coordinated strategies

Training time is 1-4 days per model

AI assists in game balancing

Abstract

In recent years, Reinforcement Learning (RL) has seen increasing popularity in research and popular culture. However, skepticism still surrounds the practicality of RL in modern video game development. In this paper, we demonstrate by example that RL can be a great tool for Artificial Intelligence (AI) design in modern, non-trivial video games. We present our RL system for Ubisoft's Roller Champions, a 3v3 Competitive Multiplayer Sports Game played on an oval-shaped skating arena. Our system is designed to keep up with agile, fast-paced development, taking 1--4 days to train a new model following gameplay changes. The AIs are adapted for various game modes, including a 2v2 mode, a Training with Bots mode, in addition to the Classic game mode where they replace players who have disconnected. We observe that the AIs develop sophisticated co-ordinated strategies, and can aid in balancing the game as an added bonus. Please see the accompanying video at https://vimeo.com/466780171 (password: rollerRWRL2020) for examples.