GDC 2024 is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

View, browse and sort the ever-growing list of sessions by day, time, pass type, topic, and format. With this Session Viewer, you can view session and speaker details for Game Developers Conference 2024.

You will be able to build your schedule with the GDC Mobile App. The GDC 2024 app will be available for download in Apple Apps and Google Play late February 2024.

Sessions do fill up and seating is first come, first serve, so arrive early to sessions that you would like to attend. Adding a session to your schedule does not guarantee you a seat.

Machine Learning Summit: 'Naruto Mobile': Optimization for Large-Scale Reinforcement Learning in Fighting Games

Elvis Liu  (Expert Engineer, Tencent Games)

Location: Room 2010, West Hall

Date: Tuesday, March 19

Time: 1:20 pm - 1:50 pm

Pass Type: All Access Pass, Summits Pass - Get your pass now!

Topic: Programming

Format: Session

Vault Recording: Video

Audience Level: All

Naruto Mobile is a popular Fighting Game with over 100 million registered players. AI agents are deployed to the game for various applications such as level challenges. Although deep reinforcement learning is an excellent approach to creating agents with diverse strategies, it is difficult to apply to Naruto Mobile--a game that is built on a pool of 300 characters with unique skills. A traditional approach of self-play training at such a scale may require substantial training costs and time. This talk presents a new training approach to improve agents' generalization ability and optimize massive-scale self-play. The proposed algorithm has already been employed by Naruto Mobile to create agents, which have been used in more than 300 million human-AI fighting matches. To the best of our knowledge to date. This is the first time that deep reinforcement learning has been employed by a commercial fighting game.


Attendees will learn about the challenges of implementing self-play reinforcement learning for fighting games, and a novel optimization method to reduce its training cost and time.

Intended Audience

This lecture is for game AI programmers and those who are interested in game AI and reinforcement learning. It would be helpful to have basic knowledge of game AI and reinforcement learning, but it is not required.

Connecting the Global Game Development Community

GDC Vault icon
Game Developers Choice Awards icon
Independent Games Festival (IGF) icon icon