Chance-Constrained Active Inference

DOI10.1162/NECO_A_01427zbMATH Open1483.91172arXiv2102.08792OpenAlexW3132290407MaRDI QIDQ5033549FDOQ5033549

Authors: Thijs van de Laar, İsmail Şenöz, Ayça Özçelikkale, Henk Wymeersch 

Publication date: 23 February 2022

Published in: Neural Computation (Search for Journal in Brave)

Abstract: Active Inference (ActInf) is an emerging theory that explains perception and action in biological agents, in terms of minimizing a free energy bound on Bayesian surprise. Goal-directed behavior is elicited by introducing prior beliefs on the underlying generative model. In contrast to prior beliefs, which constrain all realizations of a random variable, we propose an alternative approach through chance constraints, which allow for a (typically small) probability of constraint violation, and demonstrate how such constraints can be used as intrinsic drivers for goal-directed behavior in ActInf. We illustrate how chance-constrained ActInf weights all imposed (prior) constraints on the generative model, allowing e.g., for a trade-off between robust control and empirical chance constraint violation. Secondly, we interpret the proposed solution within a message passing framework. Interestingly, the message passing interpretation is not only relevant to the context of ActInf, but also provides a general purpose approach that can account for chance constraints on graphical models. The chance constraint message updates can then be readily combined with other pre-derived message update rules, without the need for custom derivations. The proposed chance-constrained message passing framework thus accelerates the search for workable models in general, and can be used to complement message-passing formulations on generative neural models.

Full work available at URL: https://arxiv.org/abs/2102.08792

Recommendations

• Active Inference: Demystified and Compared
• Generalised free energy and active inference
• Active inference, belief propagation, and the Bethe approximation
• Deep active inference
• Toward optimal probabilistic active learning using a Bayesian approach
• Active inference on discrete state-spaces: a synthesis
• Algorithmic Learning Theory

Mathematics Subject Classification ID

Psychophysics and psychophysiology; perception (91E30)

Cited In (5)

• Joint chance constrained input shaping
• Bayesian brains and the Rényi divergence
• Active Inference: Demystified and Compared
• Realizing Active Inference in Variational Message Passing: The Outcome-Blind Certainty Seeker
• Active Inference, Evidence Accumulation, and the Urn Task

This page was built for publication: Chance-Constrained Active Inference

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5033549)