# Active Inference or Control as Inference? A Unifying View

arXiv: https://arxiv.org/abs/2010.00262 · HTML: https://mlsanity.com/paper/2010.00262/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2020.

## Built on by (most cited first, 9 of 9)

- [Active Inference in Robotics and Artificial Agents: Survey and Challenges](https://mlsanity.com/paper/2112.01871/) (2021)
- [A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning](https://mlsanity.com/paper/2310.06253/) (2023)
- [Chance-Constrained Active Inference](https://mlsanity.com/paper/2102.08792/) (2021)
- [Value of Information and Reward Specification in Active Inference and POMDPs](https://mlsanity.com/paper/2408.06542/) (2024)
- [Towards Stochastic Fault-tolerant Control using Precision Learning and Active Inference](https://mlsanity.com/paper/2109.05870/) (2021)
- [A Unified View of Algorithms for Path Planning Using Probabilistic Inference on Factor Graphs](https://mlsanity.com/paper/2106.10442/) (2021)
- [Life-inspired Interoceptive Artificial Intelligence for Autonomous and Adaptive Agents](https://mlsanity.com/paper/2309.05999/) (2023)
- [Coupled autoregressive active inference agents for control of multi-joint dynamical systems](https://mlsanity.com/paper/2410.10415/) (2024)
- [Active Inference as a Convex Markov Decision Process](https://mlsanity.com/paper/2607.20152/) (2026)

## Abstract (arXiv)

Active inference (AI) is a persuasive theoretical framework from computational neuroscience that seeks to describe action and perception as inference-based computation. However, this framework has yet to provide practical sensorimotor control algorithms that are competitive with alternative approaches. In this work, we frame active inference through the lens of control as inference (CaI), a body of work that presents trajectory optimization as inference. From the wider view of `probabilistic numerics', CaI offers principled, numerically robust optimal control solvers that provide uncertainty quantification, and can scale to nonlinear problems with approximate inference. We show that AI may be framed as partially-observed CaI when the cost function is defined specifically in the observation states.