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 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.