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 day, pass type, topic, and format. With this Session Viewer, you can view GDC 2023 session details and speakers, and share your favorites via social media. You will be able to build your schedule and access it during the show via export or Mobile App, once live. Sessions do fill up and seating is first come, first serve, so arrive early to sessions that you would like to attend.

How to Implement Multi-Agent Machine Learning Scenarios in Mobile Gaming (Presented by Arm)

Koki Mitsunami  (Staff Engineer, Arm)

Location: Room 2024, West Hall

Date: Thursday, March 23

Time: 2:00 pm - 2:30 pm

Pass Type: All Access Pass, Core Pass, Summits Pass, Expo Pass, Audio Pass, Independent Games Summit Pass

Topic: Programming

Format: Sponsored Session

Vault Recording: Not Recorded

Audience Level: All

arm GlobalTrading

Arm has been investigating machine learning deployed in gaming scenarios on mobile. Attendees will hear about the motivations behind using Unity ML-Agents for this project and the main challenges and limitations of implementing ML-Agents in multi-agent scenarios on mobile. This will include how to overcome these during training and at runtime during inference. Finally, the talk will deliver conclusions and recommendations to developers planning to implement ML-Agents in multi-agent scenarios.

Takeaway

Attendees will find out about novel solutions to current limitations of ML-Agents in multi-agent scenarios on mobile, and how they can use these for their own game projects.

Intended Audience

This is an all levels talk for game developers, AI programmers and machine learning researchers who are looking to experiment with new machine learning implimentations for mobile gaming. This is also open to anyone with an interest in machine learning for mobile.