Edgar Handy (Machine Learning Engineer, SQUARE ENIX CO., LTD.)
Location: Room 2002, West Hall
Date: Monday, March 20
Time: 9:30 am - 10:30 am
All Access Pass, Summits Pass
Vault Recording: Video
Audience Level: Intermediate
Game balancing is an important aspect of quality assurance in game development, yet it's time and manpower expensive. In particular, there have been increasing practical and theoretical examples of using reinforcement learning to optimize game mechanics balancing.
However, current state-of-the-art reinforcement learning algorithms still face some key challenges, which render them less reliable. First, it requires huge volume of data and expensive hardware to learn complex game mechanics. Second, game simulators are unstable while under development process. Third, rapidly changing game mechanics that renders previously trained model useless.
In this session, Edgar Handy, Machine Learning Engineer at Square Enix, introduces a set of solutions to address these key challenges as a step to reliable ML framework for game balancing, applied to their latest flagship (unannounced) AAA title battle mechanics, resulting in a cooperation between human developers and AI on improving battle mechanics.
Attendees will gain an understanding about the current key challenges in implementing reinforcement learning for balancing AAA game battle mechanics, and the method to address them.
The is for AI/gameplay programmers, game designers, and those who are generally interested in game balancing/QA for AAA games. Basic knowledge of programming and reinforcement learning are not pre-requisite, but would be helpful to have.