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: Training Human-like and High-performance Basketball AI Bot for 'Streetball Allstar' (with introduction from Summit Advisor Julien Merceron)

Jianrong Tao  (CTO, NetEase)

Julien Merceron  (Worldwide CTO, Bandai Namco Studios)

Location: Room 2010, West Hall

Date: Tuesday, March 19

Time: 9:30 am - 10:30 am

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

Topic: Programming

Format: Session

Vault Recording: Video

Audience Level: All

"Streetball Allstar" is a 3v3 street basketball game that attracts players with its real-time competition and fairness. AI bots play an important role in the game. Firstly, they assist beginners in learning and improving, providing examples of exceptional skills and teamwork. Secondly, AI bots serve as teammates or opponents, increasing the diversity and competitiveness of the game. Most importantly, AI bots ensure fair competition, fill the gap when there are not enough players and match players of different tiers with highly customized parameters. In terms of training, we combine reinforcement learning and imitation learning, allowing AI bots to learn a wide range of strategies and simulate human thinking and behavior patterns, possessing human-like qualities and human-AI interaction while also having rich strategy diversity. Through dynamic difficulty control, we can control the operation level of the AI accurately and reasonably, adapting to different skill levels. With the client-side deployment solution, AI bots are decoupled from the core logic of game, improving response speed and ensuring data security. In our demonstration, AI bots have shown outstanding performance in various aspects such as difficulty switching, accurate response, strong adaptability, human-AI interaction, and high stability, receiving enthusiastic praise from both players and our customer.

Takeaway

In this presentation, the audience will learn about the application of AI technology in game development. Firstly, they will be introduced to "Streetball Allstar", a real-time competitive street basketball game where AI bots play an important role. The AI bots assist beginner players in learning and improving, increase the diversity and competitiveness of the game, and ensure fair competition. Secondly, the audience will learn about the training approach of AI bots using a combination of reinforcement learning and imitation learning, making them possess higher human-like qualities, human-AI interaction, and rich strategy diversity. Additionally, the audience will be introduced to the client-side deployment solution, which decouples AI bots from the core logic of game, improving response speed and ensuring data security. Finally, the effect will be demonstrated to showcase the excellent performance of AI bots in the game and user feedback. Through this presentation, the audience will gain an in-depth understanding of the application of AI technology in gaming industry, as well as how to train and deploy AI bots, and stay up-to-date with the latest technologies and trends in game development.



Connecting the Global Game Development Community

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