Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges

TL;DR

This survey reviews how reinforcement learning enhances generative AI, exploring current methods, opportunities, and open challenges in applying RL to improve generative models and embed desired traits.

Contribution

It provides a comprehensive overview of the state of the art, categorizes applications, and discusses future research directions in RL for generative AI.

Findings

RL can generate outputs without predefined objectives

RL maximizes objectives during generation

RL embeds desired traits into generative processes

Abstract

Generative Artificial Intelligence (AI) is one of the most exciting developments in Computer Science of the last decade. At the same time, Reinforcement Learning (RL) has emerged as a very successful paradigm for a variety of machine learning tasks. In this survey, we discuss the state of the art, opportunities and open research questions in applying RL to generative AI. In particular, we will discuss three types of applications, namely, RL as an alternative way for generation without specified objectives; as a way for generating outputs while concurrently maximizing an objective function; and, finally, as a way of embedding desired characteristics, which cannot be easily captured by means of an objective function, into the generative process. We conclude the survey with an in-depth discussion of the opportunities and challenges in this fascinating emerging area.