Joel Veness

Research Scientist, Google DeepMind

Research

Broadly speaking, I am interested in the algorithmic and computational aspects of Artificial Intelligence, with a particular emphasis on scalable and efficient approaches for online Reinforcement Learning agents.

Reinforcement Learning / Universal AI

I regret nothing!

Consider an agent let loose in an unknown world with only a crude reward signal and limited sensor information as feedback. An agent that can be expected to accumulate a lot of reward in many different worlds can be viewed as being generally intelligent. How might we go about designing such an agent?

 

Areas:

Universal Artificial Intelligence

Reinforcement Learning

Data Compression

Game Tree Search

Machine Learning for Games