Student research opportunities

Universal Artificial Intelligence (UAI)

Project Code: CECS_37

This project is available at the following levels:
CS single semester, Engn R&D, Honours, Summer Scholar, Masters, PhD

Keywords:

artificial intelligence; reinforcement learning; information theory; sequential decision theory; machine mearning; Bayesian statistics; philosophy of science; rational agents.

Supervisors:

Dr Peter Sunehag
Professor Marcus Hutter

Outline:

The dream of creating artificial devices that reach or outperform human intelligence is an old one. Most AI research is bottom-up, extending existing ideas and algorithms beyond their limited domain of applicability. The information-theoretic top-down approach (UAI) pursued in [Hut05] justifies, formalizes, investigates, and approximates the core of intelligence: the ability to succeed in a wide range of environments [LH07]. All other properties are emergent.
    Recently, effective approximations of UAI have been derived and experimentally investigated [VNHUS11]. This practical breakthrough has resulted in some impressive applications. For the first time, without providing any domain knowledge, the same agent is able to self-adapt to a diverse range of interactive environments. For instance, it is able to learn from scratch to play TicTacToe, Pacman, Kuhn Poker, and other games by trial and error.
    These achievements give new hope that the grand goal of Artificial General Intelligence is not elusive.

Goals of this project

The theoretical [Hut05], philosophical [LH07], and experimental [VNHUS11] foundations of UAI are already laid out, but plenty remains to be done to solve the AI problem in practice. The complexity of the open problems ranges from suitable-or-short-projects to full PhD theses and beyond.

Requirements/Prerequisites

• background in AI or ML or statistics or information theory.
  
• excellent programming or writing or math skills

Student Gain

• getting acquainted with the most comprehensive theory of rational intelligence to date.
  
• getting experience in writing a literature survey -or-
  
• advance the state-of-the art implementation of AIXI and apply it to new (toy/game) problems -or-
  
• learn how to prove non-trivial theorems.

Background Literature

• [Hut05] M. Hutter. Universal Artificial Intelligence: Sequential Decisions based on Algorithmic Probability Springer, Berlin, 2005.
  
• [LH07] S. Legg and M. Hutter. Universal intelligence: A definition of machine intelligence. Minds & Machines, 17(4):391-444, 2007.
  
• [VNHUS11] J. Veness, K. S. Ng, M. Hutter, W. Uther, and D. Silver. A Monte Carlo AIXI approximation. Journal of Artificial Intelligence Research, 40:95-142, 2011.

Contact: