Reward-Punishment Symmetric Universal Intelligence
Not on the map. Why?
Abstract (arXiv)
Can an agent's intelligence level be negative? We extend the Legg-Hutter agent-environment framework to include punishments and argue for an affirmative answer to that question. We show that if the background encodings and Universal Turing Machine (UTM) admit certain Kolmogorov complexity symmetries, then the resulting Legg-Hutter intelligence measure is symmetric about the origin. In particular, this implies reward-ignoring agents have Legg-Hutter intelligence 0 according to such UTMs.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 5 of its 24 references that are in the map. First posted on arXiv 6 Oct 2021.
Builds on
5 of 24 references.
References · 5
- 2015Bad Universal Priors and Notions of Optimalitycited by 16
- 2016Death and Suicide in Universal Artificial Intelligencecited by 9
- 2020The Archimedean trap: Why traditional reinforcement learning will probably not yield AGIcited by 6
- 2019Intelligence via ultrafilters: structural properties of some intelligence comparators of deterministic Legg-Hutter agentscited by 4
- 2021Measuring Intelligence and Growth Rate: Variations on Hibbard's Intelligence Measurecited by 3
Built on by
Citing papers per year: 2021: 2; 2022: 0; 2023: 1.
3 papers.