Derivative-Free Reinforcement Learning: A Review

TL;DR

This paper reviews the recent developments in derivative-free reinforcement learning, highlighting methods, challenges, and future directions in this emerging field that combines optimization and decision-making in unknown environments.

Contribution

It provides a comprehensive summary and organization of derivative-free reinforcement learning methods, addressing current limitations and suggesting future research directions.

Findings

Summarizes various derivative-free RL methods and their applications.

Identifies key challenges and limitations in current approaches.

Proposes future research directions for the field.

Abstract

Reinforcement learning is about learning agent models that make the best sequential decisions in unknown environments. In an unknown environment, the agent needs to explore the environment while exploiting the collected information, which usually forms a sophisticated problem to solve. Derivative-free optimization, meanwhile, is capable of solving sophisticated problems. It commonly uses a sampling-and-updating framework to iteratively improve the solution, where exploration and exploitation are also needed to be well balanced. Therefore, derivative-free optimization deals with a similar core issue as reinforcement learning, and has been introduced in reinforcement learning approaches, under the names of learning classifier systems and neuroevolution/evolutionary reinforcement learning. Although such methods have been developed for decades, recently, derivative-free reinforcement learning exhibits attracting increasing attention. However, recent survey on this topic is still lacking. In this article, we summarize methods of derivative-free reinforcement learning to date, and organize the methods in aspects including parameter updating, model selection, exploration, and parallel/distributed methods. Moreover, we discuss some current limitations and possible future directions, hoping that this article could bring more attentions to this topic and serve as a catalyst for developing novel and efficient approaches.