A Technique to Create Weaker Abstract Board Game Agents via Reinforcement Learning
This addresses the issue of overly strong AI opponents in board games for players seeking balanced gameplay, but it is incremental as it applies existing methods to new contexts.
The paper tackles the problem of creating weaker AI agents for board games to provide more suitable opponents for human players, using reinforcement learning with Q-learning on Tic-Tac-Toe, Nine-Men's Morris, and Mancala, and shows that agents can learn to play perfectly and be weakened.
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.