Investigating Enactive Learning for Autonomous Intelligent Agents
This work addresses the problem of developing alternative learning paradigms for autonomous agents, though it appears incremental in scope.
The paper investigated enactive learning for autonomous agents in foraging tasks, comparing it to classical reinforcement learning and finding that the enactive agent could learn to avoid unfavorable interactions but was limited by the number of affordable actions.
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.