A Technique to Create Weaker Abstract Board Game Agents via Reinforcement Learning

TL;DR

This paper presents a reinforcement learning approach to create intentionally weaker AI agents for board games like Tic-Tac-Toe, Nine-Men's Morris, and Mancala, enabling human players to compete against less skilled opponents.

Contribution

It introduces a method to generate weaker AI agents using Q-learning, allowing for adjustable difficulty levels in board game AI.

Findings

Weaker agents can be systematically created from perfect-playing agents.

The methodology enables comparison between different AI agents.

The approach is demonstrated on three classic board games.

Abstract

Board games, with the exception of solo games, need at least one other player to play. Because of this, we created Artificial Intelligent (AI) agents to play against us when an opponent is missing. These AI agents are created in a number of ways, but one challenge with these agents is that an agent can have superior ability compared to us. In this work, we describe how to create weaker AI agents that play board games. We use Tic-Tac-Toe, Nine-Men's Morris, and Mancala, and our technique uses a Reinforcement Learning model where an agent uses the Q-learning algorithm to learn these games. We show how these agents can learn to play the board game perfectly, and we then describe our approach to making weaker versions of these agents. Finally, we provide a methodology to compare AI agents.