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

Tim Nisslbeck; Wouter M. Kouw

doi:10.1007/978-3-031-77138-5_9

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

Tim Nisslbeck (Corresponding author), Wouter M. Kouw

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

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.

Original language	English
Title of host publication	Active Inference
Subtitle of host publication	5th International Workshop, IWAI 2024, Oxford, UK, September 9–11, 2024, Revised Selected Papers
Editors	Christopher L. Buckley, Daniela Cialfi, Pablo Lanillos, Riddhi J. Pitliya, Noor Sajid, Hideaki Shimazaki, Tim Verbelen, Martijn Wisse
Publisher	Springer
Pages	134-146
Number of pages	12
ISBN (Electronic)	978-3-031-77138-5
ISBN (Print)	978-3-031-77137-8
DOIs	https://doi.org/10.1007/978-3-031-77138-5_9
Publication status	Published - 31 Dec 2024
Event	5th International Workshop on Active Inference, IWAI 2024 - Oxford, UK, Oxford, United Kingdom Duration: 9 Sept 2024 → 11 Sept 2024

Publication series

Name	Communications in Computer and Information Science (CCIS)
Volume	2193
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	5th International Workshop on Active Inference, IWAI 2024
Abbreviated title	IWAI 2024
Country/Territory	United Kingdom
City	Oxford
Period	9/09/24 → 11/09/24

Funding

The authors gratefully acknowledge support by the Eindhoven Artificial Intelligence Systems Institute and the Ministry of Education, Culture and Science of the Government of the Netherlands.

Keywords

Active inference
Adaptive control
Autoregressive models
Bayesian filtering
Expected free energy minimization

Access to Document

10.1007/978-3-031-77138-5_9

Cite this

Nisslbeck, T., & Kouw, W. M. (2024). Coupled autoregressive active inference agents for control of multi-joint dynamical systems. In C. L. Buckley, D. Cialfi, P. Lanillos, R. J. Pitliya, N. Sajid, H. Shimazaki, T. Verbelen, & M. Wisse (Eds.), Active Inference: 5th International Workshop, IWAI 2024, Oxford, UK, September 9–11, 2024, Revised Selected Papers (pp. 134-146). (Communications in Computer and Information Science (CCIS); Vol. 2193). Springer. https://doi.org/10.1007/978-3-031-77138-5_9

Nisslbeck, Tim ; Kouw, Wouter M. / Coupled autoregressive active inference agents for control of multi-joint dynamical systems. Active Inference: 5th International Workshop, IWAI 2024, Oxford, UK, September 9–11, 2024, Revised Selected Papers. editor / Christopher L. Buckley ; Daniela Cialfi ; Pablo Lanillos ; Riddhi J. Pitliya ; Noor Sajid ; Hideaki Shimazaki ; Tim Verbelen ; Martijn Wisse. Springer, 2024. pp. 134-146 (Communications in Computer and Information Science (CCIS)).

@inproceedings{985eb6da36364df0b0b276d1271741b9,

title = "Coupled autoregressive active inference agents for control of multi-joint dynamical systems",

abstract = "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.",

keywords = "Active inference, Adaptive control, Autoregressive models, Bayesian filtering, Expected free energy minimization",

author = "Tim Nisslbeck and Kouw, \{Wouter M.\}",

year = "2024",

month = dec,

day = "31",

doi = "10.1007/978-3-031-77138-5\_9",

language = "English",

isbn = "978-3-031-77137-8",

series = "Communications in Computer and Information Science (CCIS)",

publisher = "Springer",

pages = "134--146",

editor = "Buckley, \{Christopher L.\} and Daniela Cialfi and Pablo Lanillos and Pitliya, \{Riddhi J.\} and Noor Sajid and Hideaki Shimazaki and Tim Verbelen and Martijn Wisse",

booktitle = "Active Inference",

address = "Germany",

note = "5th International Workshop on Active Inference, IWAI 2024, IWAI 2024 ; Conference date: 09-09-2024 Through 11-09-2024",

}

Nisslbeck, T & Kouw, WM 2024, Coupled autoregressive active inference agents for control of multi-joint dynamical systems. in CL Buckley, D Cialfi, P Lanillos, RJ Pitliya, N Sajid, H Shimazaki, T Verbelen & M Wisse (eds), Active Inference: 5th International Workshop, IWAI 2024, Oxford, UK, September 9–11, 2024, Revised Selected Papers. Communications in Computer and Information Science (CCIS), vol. 2193, Springer, pp. 134-146, 5th International Workshop on Active Inference, IWAI 2024, Oxford, United Kingdom, 9/09/24. https://doi.org/10.1007/978-3-031-77138-5_9

Coupled autoregressive active inference agents for control of multi-joint dynamical systems. / Nisslbeck, Tim (Corresponding author); Kouw, Wouter M.
Active Inference: 5th International Workshop, IWAI 2024, Oxford, UK, September 9–11, 2024, Revised Selected Papers. ed. / Christopher L. Buckley; Daniela Cialfi; Pablo Lanillos; Riddhi J. Pitliya; Noor Sajid; Hideaki Shimazaki; Tim Verbelen; Martijn Wisse. Springer, 2024. p. 134-146 (Communications in Computer and Information Science (CCIS); Vol. 2193).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Coupled autoregressive active inference agents for control of multi-joint dynamical systems

AU - Nisslbeck, Tim

AU - Kouw, Wouter M.

PY - 2024/12/31

Y1 - 2024/12/31

N2 - 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.

AB - 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.

KW - Active inference

KW - Adaptive control

KW - Autoregressive models

KW - Bayesian filtering

KW - Expected free energy minimization

UR - https://arxiv.org/abs/2410.10415

UR - http://www.scopus.com/inward/record.url?scp=85215778882&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-77138-5_9

DO - 10.1007/978-3-031-77138-5_9

M3 - Conference contribution

SN - 978-3-031-77137-8

T3 - Communications in Computer and Information Science (CCIS)

SP - 134

EP - 146

BT - Active Inference

A2 - Buckley, Christopher L.

A2 - Cialfi, Daniela

A2 - Lanillos, Pablo

A2 - Pitliya, Riddhi J.

A2 - Sajid, Noor

A2 - Shimazaki, Hideaki

A2 - Verbelen, Tim

A2 - Wisse, Martijn

PB - Springer

T2 - 5th International Workshop on Active Inference, IWAI 2024

Y2 - 9 September 2024 through 11 September 2024

ER -

Nisslbeck T , Kouw WM. Coupled autoregressive active inference agents for control of multi-joint dynamical systems. In Buckley CL, Cialfi D, Lanillos P, Pitliya RJ, Sajid N, Shimazaki H, Verbelen T, Wisse M, editors, Active Inference: 5th International Workshop, IWAI 2024, Oxford, UK, September 9–11, 2024, Revised Selected Papers. Springer. 2024. p. 134-146. (Communications in Computer and Information Science (CCIS)). doi: 10.1007/978-3-031-77138-5_9

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

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

CRT-STA-FEP-walker LWAI: Learning to Walk by Active Inference

Cite this

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

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Projects

CRT-STA-FEP-walker LWAI: Learning to Walk by Active Inference

Cite this