Forced ε-Greedy, an Expansion to the ε-Greedy Action Selection Method

Abstract

Reinforcement Learning methods such as Q Learning, make use of action selection methods, in order to train an agent to perform a task. As the complexity of the task grows, so does the time required to train the agent. In this paper Q Learning is applied onto the board game Dominion, and Forced ε-greedy, an expansion to the ε-greedy action selection method is introduced. As shown in this paper the Forced ε-greedy method achieves to accelerate the training process and optimize its results, especially as the complexity of the task grows.