Viet-Anh on Software Logo

What is: Epsilon Greedy Exploration?

Year2000
Data SourceCC BY-SA - https://paperswithcode.com

ϵ\epsilon-Greedy Exploration is an exploration strategy in reinforcement learning that takes an exploratory action with probability ϵ\epsilon and a greedy action with probability 1ϵ1-\epsilon. It tackles the exploration-exploitation tradeoff with reinforcement learning algorithms: the desire to explore the state space with the desire to seek an optimal policy. Despite its simplicity, it is still commonly used as an behaviour policy π\pi in several state-of-the-art reinforcement learning models.

Image Credit: Robin van Embden