Formalizing Embeddedness Failures in Universal Artificial Intelligence
On the map: Deep reinforcement learning methods → Deep RL algorithms and representations
Abstract (arXiv)
We rigorously discuss the commonly asserted failures of the AIXI reinforcement learning agent as a model of embedded agency. We attempt to formalize these failure modes and prove that they occur within the framework of universal artificial intelligence, focusing on a variant of AIXI that models the joint action/percept history as drawn from the universal distribution. We also evaluate the progress that has been made towards a successful theory of embedded agency based on variants of the AIXI agent.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 2 of its 14 references that are in the map. First posted on arXiv 23 May 2025.
Builds on
2 of 14 references.
References · 2
- 2016A Formal Solution to the Grain of Truth Problemcited by 6
- 2015Sequential Extensions of Causal and Evidential Decision Theorycited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025Embedded Universal Predictive Intelligence: a coherent framework for multi-agent learning
- 2025Architectures for Building Agentic AI
- 2025Universal AI maximizes Variational Empowerment
- 2026Artificial Agency Program: Curiosity, compression, and communication in agents
- 2025Exploring Agentic Artificial Intelligence Systems: Towards a Typological Framework
- 2026Agentic Artificial Intelligence (AI): Architectures, Taxonomies, and Evaluation of Large Language Model Agents
- 2026Agency as a New Organizing Abstraction for Computer Science
- 2026Intelligence as Managed Autonomy: Failure, Escalation, and Governance for Agentic AI Systems