Dr. Risi is a leading researcher in artificial intelligence, neural networks, and neural evolution fields with an h-index of 26 and will speak at our conference on Adaptive Game Playing Agents through Deep Neuroevolution. The summary of his speech is as follows:

Many recent breakthroughs in Artificial Intelligence (AI) would not have been possible without the help of games. Especially video games with their complex worlds and large action spaces offer unique testbeds for advanced AI methods. In this talk, I will present some of our work on creating agents that can learn to play games through deep neuroevolution, a combination of deep neural networks and evolutionary algorithms. I will show that these algorithms do not only allow agents to play games but also enable them to (1) learn 3D tasks directly from pixels, (2) learn models of the world for rapid planning, and (3) adapt quickly to task changes through a biologically-inspired form of meta-learning.