Expanding the Active Inference Landscape: More Intrinsic Motivations in the Perception-Action Loop
This work is incremental, offering a formal extension of active inference to include more intrinsic motivations, potentially benefiting researchers in active inference and intrinsic motivation by enabling comparisons and new implementations.
The paper investigates whether the inference and action selection mechanisms of active inference can be adapted to incorporate alternative intrinsic motivations beyond the original formulation, while maintaining key features like biological plausibility and robustness. It reconstructs the active inference framework, demonstrates compatibility with other intrinsic motivations, and illustrates connections to universal reinforcement learning.
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.