Back to Search
Start Over
On Epistemics in Expected Free Energy for Linear Gaussian State Space Models
- Source :
- Entropy, Entropy; Volume 23; Issue 12; Pages: 1565, Entropy, 23(12):1565. Multidisciplinary Digital Publishing Institute (MDPI), Entropy, Vol 23, Iss 1565, p 1565 (2021)
- Publication Year :
- 2021
- Publisher :
- Multidisciplinary Digital Publishing Institute (MDPI), 2021.
-
Abstract
- Active Inference (AIF) is a framework that can be used both to describe information processing in naturally intelligent systems, such as the human brain, and to design synthetic intelligent systems (agents). In this paper we show that Expected Free Energy (EFE) minimisation, a core feature of the framework, does not lead to purposeful explorative behaviour in linear Gaussian dynamical systems. We provide a simple proof that, due to the specific construction used for the EFE, the terms responsible for the exploratory (epistemic) drive become constant in the case of linear Gaussian systems. This renders AIF equivalent to KL control. From a theoretical point of view this is an interesting result since it is generally assumed that EFE minimisation will always introduce an exploratory drive in AIF agents. While the full EFE objective does not lead to exploration in linear Gaussian dynamical systems, the principles of its construction can still be used to design objectives that include an epistemic drive. We provide an in-depth analysis of the mechanics behind the epistemic drive of AIF agents and show how to design objectives for linear Gaussian dynamical systems that do include an epistemic drive. Concretely, we show that focusing solely on epistemics and dispensing with goal-directed terms leads to a form of maximum entropy exploration that is heavily dependent on the type of control signals driving the system. Additive controls do not permit such exploration. From a practical point of view this is an important result since linear Gaussian dynamical systems with additive controls are an extensively used model class, encompassing for instance Linear Quadratic Gaussian controllers. On the other hand, linear Gaussian dynamical systems driven by multiplicative controls such as switching transition matrices do permit an exploratory drive.
- Subjects :
- Minimisation (psychology)
Mathematical optimization
Dynamical systems theory
Computer science
Science
QC1-999
Gaussian
General Physics and Astronomy
Astrophysics
Linear-quadratic-Gaussian control
active inference
epistemics
expected free energy
free energy principle
linear Gaussian dynamical system
Expected free energy
Article
Epistemics
symbols.namesake
Design objective
State space
Free energy principle
Physics
Intelligent decision support system
QB460-466
Linear Gaussian dynamical system
symbols
Active inference
Subjects
Details
- Language :
- English
- ISSN :
- 10994300
- Volume :
- 23
- Issue :
- 12
- Database :
- OpenAIRE
- Journal :
- Entropy
- Accession number :
- edsair.doi.dedup.....3b76e14fd76642b401a501fb369aa53a