Quantum AIXI: Universal Intelligence via Quantum Information
Elija Perrier

TL;DR
This paper introduces Quantum AIXI (QAIXI), a quantum extension of the classical AIXI model for artificial general intelligence, incorporating quantum information principles to better align with the quantum nature of the universe.
Contribution
The paper develops a quantum framework for AIXI, including quantum agent-environment interactions, quantum Kolmogorov complexity, and a QAIXI value function, advancing the theoretical foundation of quantum AGI.
Findings
Quantum AIXI models can incorporate both classical and quantum actions.
Quantum contextuality influences the structure and limitations of QAIXI.
Quantum Solomonoff induction faces specific conditions and limitations.
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsQuantum Computing Algorithms and Architecture
