Joel Veness

Research

Broadly speaking, I am interested in Artificial Intelligence and Machine Learning. My main motivation stems from a belief that AI research (within the next 30 years) will have an enormous impact on society.

Reinforcement Learning / Universal AI

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 scenarios can be viewed as being generally intelligent, in some sense of the word. How might we go about designing such an agent?

'I apologise... for nothing' - Hedonism Bot, Futurama.

Machine Learning for Games

People have been able to create programs that play at a superhuman level in a number of games. To what extent can we automate this task?