The Free Energy Principle for Perception and Action: A Deep Learning Perspective

Abstract

The free energy principle, and its corollary active inference, constitute a bio-inspired theory that assumes biological agents act to remain in a restricted set of preferred states of the world, i.e., they minimize their free energy. Under this principle, biological agents learn a generative model of the world and plan actions in the future that will maintain the agent in an homeostatic state that satisfies its preferences. This framework lends itself to being realized in silico, as it comprehends important aspects that make it computationally affordable, such as variational inference and amortized planning. In this work, we investigate the tool of deep learning to design and realize artificial agents based on active inference, presenting a deep-learning oriented presentation of the free energy principle, surveying works that are relevant in both machine learning and active inference areas, and discussing the design choices that are involved in the implementation process. This manuscript probes newer perspectives for the active inference framework, grounding its theoretical aspects into more pragmatic affairs, offering a practical guide to active inference newcomers and a starting point for deep learning practitioners that would like to investigate implementations of the free energy principle.

Nothing but a useful tool? (F)utility and the free-energy principle

“…The implication of breaking this assumption is that the FEP is actually doing its most interesting work away from steady state, and therefore without Friston blankets. This seems to contradict the large body of work on models based on active inference formulations where past information appears to play a crucial role (see for instance Baltieri & Isomura, 2021;Isomura, Shimazaki, & Friston, 2022;Lanillos et al, 2021;Mazzaglia, Verbelen, Çatal, & Dhoedt, 2022; to give only a few recent examples). It is crucial, however, to highlight that the stipulative nature of Friston blankets is not playing any role in these modelsactive inference can and does exist without Friston blankets.…”

The Emperor Is Naked: Replies to commentaries on the target article

“…The implication of breaking this assumption is that the FEP is actually doing its most interesting work away from steady state, and therefore without Friston blankets. This seems to contradict the large body of work on models based on active inference formulations where past information appears to play a crucial role (see for instance Baltieri & Isomura, 2021; Friston et al, 2015, 2017a, 2017b; Isomura, Shimazaki, & Friston, 2022; Lanillos et al, 2021; Mazzaglia, Verbelen, Çatal, & Dhoedt, 2022; Parr & Friston, 2019 – to give only a few recent examples). It is crucial, however, to highlight that the stipulative nature of Friston blankets is not playing any role in these models – active inference can and does exist without Friston blankets.…”

Disentangling Shape and Pose for Object-Centric Deep Active Inference Models

“…In this paper, we propose a novel model which encourages a disentangled latent space, and we compare with other deep active inference models such as [33] and [17]. For a more extensive review, see [19].…”