Investigating Enactive Learning for Autonomous Intelligent Agents

TL;DR

This paper explores enactive learning in artificial agents, comparing it to reinforcement learning in maze foraging tasks, highlighting its capabilities and limitations in sensorimotor interaction-based cognition.

Contribution

It introduces an enactive learning framework for artificial agents and evaluates its performance against classical reinforcement learning in simulated environments.

Findings

Enactive agents can successfully learn to avoid unfavorable interactions.

Performance is limited by the number of available actions.

Enactive approach emphasizes sensorimotor interaction over internal representations.

Abstract

The enactive approach to cognition is typically proposed as a viable alternative to traditional cognitive science. Enactive cognition displaces the explanatory focus from the internal representations of the agent to the direct sensorimotor interaction with its environment. In this paper, we investigate enactive learning through means of artificial agent simulations. We compare the performances of the enactive agent to an agent operating on classical reinforcement learning in foraging tasks within maze environments. The characteristics of the agents are analysed in terms of the accessibility of the environmental states, goals, and exploration/exploitation tradeoffs. We confirm that the enactive agent can successfully interact with its environment and learn to avoid unfavourable interactions using intrinsically defined goals. The performance of the enactive agent is shown to be limited by the number of affordable actions.