# Games of Knightian Uncertainty as AGI testbeds

arXiv: https://arxiv.org/abs/2406.18178 · HTML: https://mlsanity.com/paper/2406.18178/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 26 references that are in the map.
- First posted on arXiv 26 Jun 2024.

## Builds on (most cited first, 14 of 14)

- [Compositionality decomposed: how do neural networks generalise?](https://mlsanity.com/paper/1908.08351/) (2019)
- [Causality for Machine Learning](https://mlsanity.com/paper/1911.10500/) (2019)
- [Optimal Policies Tend to Seek Power](https://mlsanity.com/paper/1912.01683/) (2019)
- [Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions](https://mlsanity.com/paper/2003.08536/) (2020)
- [Abstraction and Analogy-Making in Artificial Intelligence](https://mlsanity.com/paper/2102.10717/) (2021)
- [Levels of AGI for Operationalizing Progress on the Path to AGI](https://mlsanity.com/paper/2311.02462/) (2023)
- [Robust agents learn causal world models](https://mlsanity.com/paper/2402.10877/) (2024)
- [A Review of Uncertainty for Deep Reinforcement Learning](https://mlsanity.com/paper/2208.09052/) (2022)
- [MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2303.03376/) (2023)
- [Which Mutual-Information Representation Learning Objectives are Sufficient for Control?](https://mlsanity.com/paper/2106.07278/) (2021)
- [Adversarial Policies Beat Superhuman Go AIs](https://mlsanity.com/paper/2211.00241/) (2022)
- [General Intelligence Requires Rethinking Exploration](https://mlsanity.com/paper/2211.07819/) (2022)
- [AI Researchers, Video Games Are Your Friends!](https://mlsanity.com/paper/1612.01608/) (2016)
- [An Overview of the Ludii General Game System](https://mlsanity.com/paper/1907.00240/) (2019)

## Abstract (arXiv)

Arguably, for the latter part of the late 20th and early 21st centuries, games have been seen as the drosophila of AI. Games are a set of exciting testbeds, whose solutions (in terms of identifying optimal players) would lead to machines that would possess some form of general intelligence, or at the very least help us gain insights toward building intelligent machines. Following impressive successes in traditional board games like Go, Chess, and Poker, but also video games like the Atari 2600 collection, it is clear that this is not the case. Games have been attacked successfully, but we are nowhere near AGI developments (or, as harsher critics might say, useful AI developments!). In this short vision paper, we argue that for game research to become again relevant to the AGI pathway, we need to be able to address textitKnightian uncertainty in the context of games, i.e. agents need to be able to adapt to rapid changes in game rules on the fly with no warning, no previous data, and no model access.