Towards autonomous artificial agents with an active self: modeling sense of control in situated action

TL;DR

This paper proposes a computational model for an active self in artificial agents, integrating sensorimotor learning and cognitive control to develop a sense of control that enhances autonomous action in unpredictable environments.

Contribution

It introduces a novel embodied cognitive architecture based on predictive processing and free energy minimization for modeling an agent's sense of control.

Findings

The model demonstrates how a sense of control forms across control hierarchy levels.

Different parameter settings influence the integration of low- and high-level control.

The sense of control improves the agent's adaptability in unpredictable situations.

Abstract

In this paper we present a computational modeling account of an active self in artificial agents. In particular we focus on how an agent can be equipped with a sense of control and how it arises in autonomous situated action and, in turn, influences action control. We argue that this requires laying out an embodied cognitive model that combines bottom-up processes (sensorimotor learning and fine-grained adaptation of control) with top-down processes (cognitive processes for strategy selection and decision-making). We present such a conceptual computational architecture based on principles of predictive processing and free energy minimization. Using this general model, we describe how a sense of control can form across the levels of a control hierarchy and how this can support action control in an unpredictable environment. We present an implementation of this model as well as first evaluations in a simulated task scenario, in which an autonomous agent has to cope with un-/predictable situations and experiences corresponding sense of control. We explore different model parameter settings that lead to different ways of combining low-level and high-level action control. The results show the importance of appropriately weighting information in situations where the need for low/high-level action control varies and they demonstrate how the sense of control can facilitate this.