GDC 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 pass type, topic, and format. All registered attendees will be able to build their personal schedule in the mobile event app, once live early 2022.

GDC Masterclass courses require a paid pass to attend. Class sizes are kept intentionally small and seats are limited to ensure every student receives one-on-one assistance from the instructor. Pass pricing per course varies, please review the passes and pricing page for more details and secure your spot today!

Reinforcement Learning for Efficient Cars and Tracks Design in Racing Games

Minggao Wei  (Senior AI Engineer, NetEase Games AI Lab)

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

Topic: Programming

Format: Session

Vault Recording: TBD

Audience Level: No

Traditionally in a racing game, it is time-consuming for the game designers to manually verify and adjust the performance of cars on every track. This presentation introduces an AI-driven approach based on deep reinforcement learning to free the designers from boring repetitions. With this technique, the optimal racing trace for all cars can be figured out in less than an hour, making it possible to do a thorough evaluation. Besides that, the drift area, which is highly related to the track difficulty, can be visualized to help the assessment. Even without the game designers' prior knowledge, this AI system considerably reduces the game development lifetime and provides a more accurate and balanced analysis.


Attendees will leave with the experience of training AI in racing games through reinforcement learning and will also learn how to use such an AI to help design games.

Intended Audience

Game designers who are interested in AI techniques and care about the efficiency of game design, and developers who are interested in building such AIs.