pith. sign in

arxiv: 2606.08369 · v1 · pith:EIL5LHWRnew · submitted 2026-06-06 · 💻 cs.LG · cs.AI

An Information-Theoretic Definition for Open-Ended Learning

classification 💻 cs.LG cs.AI
keywords open-endedenvironmentdefinitionagentattainbanditbit-equivalentinformation-theoretic
0
0 comments X
read the original abstract

A growing body of work points to the great promise of AI systems that can continually expand their capabilities as they operate in an open-ended environment. But yet there is no coherent definition of open-endedness or theory about how an agent ought to explore an open-ended environment. We introduce an information-theoretic definition based on a new concept -- the ${\textit bit-equivalent}$ -- which quantifies the information required to attain each level of expected reward. We consider an environment to be open-ended if an agent can attain linear growth in the bit-equivalent. We establish that classical bandit environments are not open-ended and formulate a bandit environment that is. We also introduce an algorithm that achieves open-ended learning in this environment.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.