Search
 
loader loading subjects...
cover
Forced ε-Greedy, an Expansion to the ε-Greedy Action Selection Method
George Angelopoulos, Dimitris Metafas
12 - 20
10.3233/FAIA210070
Research Article
Frontiers in Artificial Intelligence and Applications
Volume 338: Novelties in Intelligent Digital Systems
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.

Download
Creative Commons License