Given a probabilistic model, RxInfer allows for an efficient message-passing based Bayesian inference. It uses the model structure to generate an algorithm that consists of a sequence of local computations on a Forney-style factor graph (FFG) representation of the model.
Toward Design of
Synthetic Active Inference Agents
by Mere Mortals
Bert de Vries
Eindhoven University of Technology
Eindhoven, the Netherlands
bert.de.vries@tue.nl
July 27, 2023
Abstract
The theoretical properties of active inference agents are impressive,
but how do we realize effective agents in working hardware and software
on edge devices? This is an interesting problem because the computa�tional load for policy exploration explodes exponentially, while the com�putational resources are very limited for edge devices. In this paper, we
discuss the necessary features for a software toolbox that supports a com�petent non-expert engineer to develop working active inference agents. We
introduce a toolbox-in-progress that aims to accelerate the democratiza�tion of active inference agents in a similar way as TensorFlow propelled
applications of deep learning technology.
Given a probabilistic model, RxInfer allows for an efficient message-passing based Bayesian inference. It uses the model structure to generate an algorithm that consists of a sequence of local computations on a Forney-style factor graph (FFG) representation of the model.
Toward Design of
Synthetic Active Inference Agents
by Mere Mortals
Bert de Vries
Eindhoven University of Technology
Eindhoven, the Netherlands
bert.de.vries@tue.nl
July 27, 2023
Abstract
The theoretical properties of active inference agents are impressive,
but how do we realize effective agents in working hardware and software
on edge devices? This is an interesting problem because the computa�tional load for policy exploration explodes exponentially, while the com�putational resources are very limited for edge devices. In this paper, we
discuss the necessary features for a software toolbox that supports a com�petent non-expert engineer to develop working active inference agents. We
introduce a toolbox-in-progress that aims to accelerate the democratiza�tion of active inference agents in a similar way as TensorFlow propelled
applications of deep learning technology.