Abstract

The dream of creating artificial devices that reach or outperform human intelligence is many centuries old. In this talk I present an elegant parameter-free theory of an optimal reinforcement learning agent embedded in an arbitrary unknown environment that possesses essentially all aspects of rational intelligence. The theory reduces all conceptual AI problems to pure computational questions. The necessary and sufficient ingredients are Bayesian probability theory; algorithmic information theory; universal Turing machines; the agent framework; sequential decision theory; and reinforcement learning, which are all important subjects in their own right. I also present some recent approximations, implementations, and applications of this modern top-down approach to AI.