Universal Algorithmic Intelligence

Elija Perrier will discuss his work on quantum mechanical versions of the AIXI agent: https://arxiv.org/abs/2505.21170

The (extra) talk will be tomorrow, Monday Feb 16th at 3 pm EST over the usual zoom link.

Bio

Elija is a doctoral candidate at the Centre for Quantum Software and Information at the University of Technology Sydney. Elija’s doctoral research focuses on the field of quantum machine learning, including quantum algorithm design, geometric and statistical learning theory and quantum control. He has a multi-disciplinary background, holding an LLB / BA (Hons) (English/Cultural & Communication Studies) from Murdoch University along with a BSc (Physics/Mathematics) (Hons) & BA (Economics/Philosophy) from the University of Sydney. He is a practising lawyer, and has worked as a research assistant in the School of Economics at the University of Sydney, a tutor in constitutional law and jurisprudence at Macquarie University and as a data scientist focusing on political science. Elija has published research on computer science, public policy and a range of other topics and has presented research at a number of conferences nationally and internationally.

Abstract

AIXI is a widely studied model of artificial general intelligence (AGI) based upon principles of induction and reinforcement learning. However, AIXI is fundamentally classical in nature – as are the environments in which it is modelled. Given the universe is quantum mechanical in nature and the exponential overhead required to simulate quantum mechanical systems classically, the question arises as to whether there are quantum mechanical analogues of AIXI. To address this question, we extend the framework to quantum information and present Quantum AIXI (QAIXI). We introduce a model of quantum agent/environment interaction based upon quantum and classical registers and channels, showing how quantum AIXI agents may take both classical and quantum actions. We formulate the key components of AIXI in quantum information terms, extending previous research on quantum Kolmogorov complexity and a QAIXI value function. We discuss conditions and limitations upon quantum Solomonoff induction and show how contextuality fundamentally affects QAIXI models.