Temporally-Extended ε-Greedy Exploration

Code

• github.com/oh-lab/UTE-Uncertainty-aware-Temporal-Extension-
  pytorch★ 1

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 -greedy. In this paper we propose an exploration algorithm that retains the simplicity of -greedy while reducing dithering. We build on a simple hypothesis: the main limitation of -greedy exploration is its lack of temporal persistence, which limits its ability to escape local optima. We propose a temporally extended form of -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.

Tasks

Reproductions