3D Érzékelés és Mobilrobotika Kutatócsoport

Video Games AI

The idea of developing autonomous agents using reinforcement learning has seen many recent successes, including AlphaGo’s memorable victory. While using AI to play games may seem like a rather childish endeavour, games actually produce a very safe environment to test AI’s ability to develop an understanding of the physical world. Since most video games are made about certain aspects of the real world, developing AI that is able to play these games well may pave the way for autonomous robots that can interact with the physical world safely and productively.

In our lab we focus on using deep reinforcement learning to produce intelligent agents for video games. Our focus is mainly on video games that need visual and spatial understanding in order to be played well. We are developing AI for existing environments, such as the ones found in OpenAI’s Gym, as well as developing new environment for increasingly complex games.