Saved in:
Bibliographic Details
Main Authors: Wyeth, Cole, Hutter, Marcus
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.17882
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918032094265344
author Wyeth, Cole
Hutter, Marcus
author_facet Wyeth, Cole
Hutter, Marcus
contents We rigorously discuss the commonly asserted failures of the AIXI reinforcement learning agent as a model of embedded agency. We attempt to formalize these failure modes and prove that they occur within the framework of universal artificial intelligence, focusing on a variant of AIXI that models the joint action/percept history as drawn from the universal distribution. We also evaluate the progress that has been made towards a successful theory of embedded agency based on variants of the AIXI agent.
format Preprint
id arxiv_https___arxiv_org_abs_2505_17882
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Formalizing Embeddedness Failures in Universal Artificial Intelligence
Wyeth, Cole
Hutter, Marcus
Artificial Intelligence
We rigorously discuss the commonly asserted failures of the AIXI reinforcement learning agent as a model of embedded agency. We attempt to formalize these failure modes and prove that they occur within the framework of universal artificial intelligence, focusing on a variant of AIXI that models the joint action/percept history as drawn from the universal distribution. We also evaluate the progress that has been made towards a successful theory of embedded agency based on variants of the AIXI agent.
title Formalizing Embeddedness Failures in Universal Artificial Intelligence
topic Artificial Intelligence
url https://arxiv.org/abs/2505.17882