## Tags - Part of: [[Game theory]] [[Evolutionary game theory]] [[Artificial Intelligence]] [[Reinforcement learning]] [[Economics]] [[Free energy principle]] [[Machine learning]] [[Mathematics]] - Related: - Includes: - Additional: ## Definitions - Research direction that asks: Some [[Systems science|systems]] in the world seem to behave like “[[Agent|agents]]”: they make consistent decisions, and sometimes display complex goal-seeking behaviour. Can we develop a robust [[Mathematics|mathematical]] description of such systems and build provably aligned AI agents? ## Main resources - [Artificial Intelligence @ MIRI](https://intelligence.org) - <iframe src="https://intelligence.org" allow="fullscreen" allowfullscreen="" style="height:100%;width:100%; aspect-ratio: 16 / 5; "></iframe> ## Landscapes - [Agent Foundations - AI Alignment Forum](https://www.alignmentforum.org/tag/agent-foundations) - [Artificial Intelligence @ MIRI](/) ## Additional resources - [Why Agent Foundations? An Overly Abstract Explanation — LessWrong](https://www.lesswrong.com/posts/FWvzwCDRgcjb9sigb/why-agent-foundations-an-overly-abstract-explanation)