Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.10415 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913544945008640 |
|---|---|
| author | Nisslbeck, Tim N. Kouw, Wouter M. |
| author_facet | Nisslbeck, Tim N. Kouw, Wouter M. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_10415 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Coupled autoregressive active inference agents for control of multi-joint dynamical systems Nisslbeck, Tim N. Kouw, Wouter M. Machine Learning Systems and Control 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. |
| title | Coupled autoregressive active inference agents for control of multi-joint dynamical systems |
| topic | Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2410.10415 |