# Toward Idealized Decision Theory

arXiv: https://arxiv.org/abs/1507.01986 · HTML: https://mlsanity.com/paper/1507.01986/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jul 2015.

## Built on by (most cited first, 2 of 2)

- [A dataset of questions on decision-theoretic reasoning in Newcomb-like problems](https://mlsanity.com/paper/2411.10588/) (2024)
- [Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignment](https://mlsanity.com/paper/2406.11039/) (2024)

## Abstract (arXiv)

This paper motivates the study of decision theory as necessary for aligning smarter-than-human artificial systems with human interests. We discuss the shortcomings of two standard formulations of decision theory, and demonstrate that they cannot be used to describe an idealized decision procedure suitable for approximation by artificial systems. We then explore the notions of policy selection and logical counterfactuals, two recent insights into decision theory that point the way toward promising paths for future research.