Evolutionary Algorithms for Reinforcement Learning

TL;DR

This paper reviews the application of evolutionary algorithms to reinforcement learning, highlighting different policy representations, credit assignment techniques, and genetic operators, along with their strengths, weaknesses, and applications.

Contribution

It provides a comprehensive survey of how evolutionary algorithms are used in reinforcement learning, emphasizing alternative methods and recent developments.

Findings

Evolutionary algorithms offer flexible policy representations.

They have unique strengths and weaknesses compared to other RL methods.

Applications demonstrate the versatility of evolutionary approaches in RL.

Abstract

There are two distinct approaches to solving reinforcement learning problems, namely, searching in value function space and searching in policy space. Temporal difference methods and evolutionary algorithms are well-known examples of these approaches. Kaelbling, Littman and Moore recently provided an informative survey of temporal difference methods. This article focuses on the application of evolutionary algorithms to the reinforcement learning problem, emphasizing alternative policy representations, credit assignment methods, and problem-specific genetic operators. Strengths and weaknesses of the evolutionary approach to reinforcement learning are presented, along with a survey of representative applications.