Keywords: reinforcement learning, exploration
Abstract: Recent work on exploration in reinforcement learning (RL) has led to a series of increasingly complex solutions to the problem. This increase in complexity often comes at the expense of generality. Recent empirical studies suggest that, when applied to a broader set of domains, some sophisticated exploration methods are outperformed by simpler counterparts, such as ε-greedy. In this paper we propose an exploration algorithm that retains the simplicity of ε-greedy while reducing dithering. We build on a simple hypothesis: the main limitation of ε-greedy exploration is its lack of temporal persistence, which limits its ability to escape local optima. We propose a temporally extended form of ε-greedy that simply repeats the sampled action for a random duration. It turns out that, for many duration distributions, this suffices to improve exploration on a large set of domains. Interestingly, a class of distributions inspired by ecological models of animal foraging behaviour yields particularly strong performance.
One-sentence Summary: We discuss a new framework for option-based exploration, present a thorough empirical study of a simple, generally applicable set of options within this framework, and observe improved performance over state-of-the-art agents and exploration methods.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Data: [Arcade Learning Environment](https://paperswithcode.com/dataset/arcade-learning-environment)