# Unbiased Active Inference for Classical Control

arXiv: https://arxiv.org/abs/2207.13409 · HTML: https://mlsanity.com/paper/2207.13409/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jul 2022.

## Built on by (most cited first, 2 of 2)

- [Seeing Through Uncertainty: Free-Energy-Inspired Real-Time Adaptation for Robust Visual Navigation](https://mlsanity.com/paper/2403.01977/) (2024)
- [Information as Maximum-Caliber Deviation: A bridge between Integrated Information Theory and the Free Energy Principle](https://mlsanity.com/paper/2605.12536/) (2026)

## Abstract (arXiv)

Active inference is a mathematical framework that originated in computational neuroscience. Recently, it has been demonstrated as a promising approach for constructing goal-driven behavior in robotics. Specifically, the active inference controller (AIC) has been successful on several continuous control and state-estimation tasks. Despite its relative success, some established design choices lead to a number of practical limitations for robot control. These include having a biased estimate of the state, and only an implicit model of control actions. In this paper, we highlight these limitations and propose an extended version of the unbiased active inference controller (u-AIC). The u-AIC maintains all the compelling benefits of the AIC and removes its limitations. Simulation results on a 2-DOF arm and experiments on a real 7-DOF manipulator show the improved performance of the u-AIC with respect to the standard AIC. The code can be found at https://github.com/cpezzato/unbiased_aic.