Active Inference and Epistemic Value in Graphical Models

by   Thijs van de Laar, et al.

The Free Energy Principle (FEP) postulates that biological agents perceive and interact with their environment in order to minimize a Variational Free Energy (VFE) with respect to a generative model of their environment. The inference of a policy (future control sequence) according to the FEP is known as Active Inference (AIF). The AIF literature describes multiple VFE objectives for policy planning that lead to epistemic (information-seeking) behavior. However, most objectives have limited modeling flexibility. This paper approaches epistemic behavior from a constrained Bethe Free Energy (CBFE) perspective. Crucially, variational optimization of the CBFE can be expressed in terms of message passing on free-form generative models. The key intuition behind the CBFE is that we impose a point-mass constraint on predicted outcomes, which explicitly encodes the assumption that the agent will make observations in the future. We interpret the CBFE objective in terms of its constituent behavioral drives. We then illustrate resulting behavior of the CBFE by planning and interacting with a simulated T-maze environment. Simulations for the T-maze task illustrate how the CBFE agent exhibits an epistemic drive, and actively plans ahead to account for the impact of predicted outcomes. Compared to an EFE agent, the CBFE agent incurs expected reward in significantly more environmental scenarios. We conclude that CBFE optimization by message passing suggests a general mechanism for epistemic-aware AIF in free-form generative models.



There are no comments yet.


page 24

page 26

page 29


Chance-Constrained Active Inference

Active Inference (ActInf) is an emerging theory that explains perception...

Whence the Expected Free Energy?

The Expected Free Energy (EFE) is a central quantity in the theory of ac...

Demystifying active inference

Active inference is a first (Bayesian) principles account of how autonom...

Realising Active Inference in Variational Message Passing: the Outcome-blind Certainty Seeker

Active inference is a state-of-the-art framework in neuroscience that of...

AIDA: An Active Inference-based Design Agent for Audio Processing Algorithms

In this paper we present AIDA, which is an active inference-based agent ...

Active inference, Bayesian optimal design, and expected utility

Active inference, a corollary of the free energy principle, is a formal ...

Contrastive Active Inference

Active inference is a unifying theory for perception and action resting ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.