Causally embedded learning

Perhaps more interesting part of what actually mean by ‘embodiment’

2025-12-22 — 2026-01-02

Wherein causal embedding is presented as a lens for resolving debates about embodiment and stochastic parrotology, and the role of a bronze Buddha illustration is invoked to mark a contemplative example.

evolution
snarks
Figure 1

When people talk about embodiment they’re questioning whether the body is a necessary part of the mind. When they ask about stochastic parrotology, they’re wondering whether interacting with the world is a necessary part of agency.

I suspect both of these frustratingly vague families of questions can be made more precise by considering the idea of causal embedding. Maybe we could also better understand empowerment and ecology of mind better.

Let’s see. Formalisms to come.

1 References

Demski, and Garrabrant. 2020. Embedded Agency.”
Dobbyn, and Stuart. 2003. The Self as an Embedded Agent.” Minds and Machines.
Everitt, Carey, Langlois, et al. 2021. Agent Incentives: A Causal Perspective.” In Proceedings of the AAAI Conference on Artificial Intelligence.
Foerster, Chen, Al-Shedivat, et al. 2018. Learning with Opponent-Learning Awareness.” In Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems. AAMAS ’18.
Hammond, Fox, Everitt, et al. 2023. Reasoning about Causality in Games.” Artificial Intelligence.
Hewson. 2024. We Urgently Need Intrinsically Kind Machines.”
Lowe, Edelman, Zhi-Xuan, et al. 2025. Full-Stack Alignment: Co-Aligning AI and Institutions with Thicker Models of Value.” In.
Meulemans, Nasser, Wołczyk, et al. 2025. Embedded Universal Predictive Intelligence: A Coherent Framework for Multi-Agent Learning.”
Wolpert, and Kinney. 2023. Stochastic Mathematical Systems.”
———. 2024. A Stochastic Model of Mathematics and Science.” Foundations of Physics.
Wyeth, and Hutter. 2025. Formalizing Embeddedness Failures in Universal Artificial Intelligence.” In.