# Coupled autoregressive active inference agents for control of multi-joint dynamical systems

arXiv: https://arxiv.org/abs/2410.10415 · HTML: https://mlsanity.com/paper/2410.10415/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 29 references that are in the map.
- First posted on arXiv 14 Oct 2024.

## Builds on (most cited first, 9 of 9)

- [Active inference on discrete state-spaces: a synthesis](https://mlsanity.com/paper/2001.07203/) (2020)
- [Active Inference in Robotics and Artificial Agents: Survey and Challenges](https://mlsanity.com/paper/2112.01871/) (2021)
- [Deep Active Inference](https://mlsanity.com/paper/1709.02341/) (2017)
- [Deep Active Inference for Partially Observable MDPs](https://mlsanity.com/paper/2009.03622/) (2020)
- [Active Inference for Integrated State-Estimation, Control, and Learning](https://mlsanity.com/paper/2005.05894/) (2020)
- [Active Inference or Control as Inference? A Unifying View](https://mlsanity.com/paper/2010.00262/) (2020)
- [Active Inference and Epistemic Value in Graphical Models](https://mlsanity.com/paper/2109.00541/) (2021)
- [Information-seeking polynomial NARX model-predictive control through expected free energy minimization](https://mlsanity.com/paper/2312.15046/) (2023)
- [Learning Policies for Continuous Control via Transition Models](https://mlsanity.com/paper/2209.08033/) (2022)

## Built on by (most cited first, 1 of 1)

- [Online Bayesian system identification in multivariate autoregressive models via message passing](https://mlsanity.com/paper/2506.02710/) (2025)

## Abstract (arXiv)

We propose an active inference agent to identify and control a mechanical system with multiple bodies connected by joints. This agent is constructed from multiple scalar autoregressive model-based agents, coupled together by virtue of sharing memories. Each subagent infers parameters through Bayesian filtering and controls by minimizing expected free energy over a finite time horizon. We demonstrate that a coupled agent of this kind is able to learn the dynamics of a double mass-spring-damper system, and drive it to a desired position through a balance of explorative and exploitative actions. It outperforms the uncoupled subagents in terms of surprise and goal alignment.