Q-Learning with Basic Emotions

TL;DR

This paper introduces an affective Q-learning agent influenced by basic emotions, demonstrating improved efficiency in finding optimal paths with fewer steps and a decreasing exploration-exploitation ratio.

Contribution

It proposes integrating four basic emotions into Q-learning to enhance learning efficiency and reduce the number of steps needed to find optimal solutions.

Findings

Affective agent requires fewer steps to find optimal paths.

The exploration-exploitation ratio decreases over time.

Affective influence improves learning efficiency.

Abstract

Q-learning is a simple and powerful tool in solving dynamic problems where environments are unknown. It uses a balance of exploration and exploitation to find an optimal solution to the problem. In this paper, we propose using four basic emotions: joy, sadness, fear, and anger to influence a Qlearning agent. Simulations show that the proposed affective agent requires lesser number of steps to find the optimal path. We found when affective agent finds the optimal path, the ratio between exploration to exploitation gradually decreases, indicating lower total step count in the long run