Expanding the Active Inference Landscape: More Intrinsic Motivations in the Perception-Action Loop

TL;DR

This paper explores how the active inference framework can incorporate various intrinsic motivations, expanding its applicability and linking it to universal reinforcement learning, while maintaining biological plausibility.

Contribution

It demonstrates how alternative intrinsic motivations can be integrated into active inference without losing its core features and connects this approach to universal reinforcement learning.

Findings

Active inference can incorporate alternative intrinsic motivations.

The formalism links active inference to universal reinforcement learning.

Alternative intrinsic motivations induce different dynamics in perception-action loops.

Abstract

Active inference is an ambitious theory that treats perception, inference and action selection of autonomous agents under the heading of a single principle. It suggests biologically plausible explanations for many cognitive phenomena, including consciousness. In active inference, action selection is driven by an objective function that evaluates possible future actions with respect to current, inferred beliefs about the world. Active inference at its core is independent from extrinsic rewards, resulting in a high level of robustness across e.g.\ different environments or agent morphologies. In the literature, paradigms that share this independence have been summarised under the notion of intrinsic motivations. In general and in contrast to active inference, these models of motivation come without a commitment to particular inference and action selection mechanisms. In this article, we study if the inference and action selection machinery of active inference can also be used by alternatives to the originally included intrinsic motivation. The perception-action loop explicitly relates inference and action selection to the environment and agent memory, and is consequently used as foundation for our analysis. We reconstruct the active inference approach, locate the original formulation within, and show how alternative intrinsic motivations can be used while keeping many of the original features intact. Furthermore, we illustrate the connection to universal reinforcement learning by means of our formalism. Active inference research may profit from comparisons of the dynamics induced by alternative intrinsic motivations. Research on intrinsic motivations may profit from an additional way to implement intrinsically motivated agents that also share the biological plausibility of active inference.