Reward Models in Deep Reinforcement Learning: A Survey

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yu, Rui, Wan, Shenghua, Wang, Yucen, Gao, Chen-Xiao, Gan, Le, Zhang, Zongzhang, Zhan, De-Chuan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911011936665600
author Yu, Rui
Wan, Shenghua
Wang, Yucen
Gao, Chen-Xiao
Gan, Le
Zhang, Zongzhang
Zhan, De-Chuan
author_facet Yu, Rui
Wan, Shenghua
Wang, Yucen
Gao, Chen-Xiao
Gan, Le
Zhang, Zongzhang
Zhan, De-Chuan
contents In reinforcement learning (RL), agents continually interact with the environment and use the feedback to refine their behavior. To guide policy optimization, reward models are introduced as proxies of the desired objectives, such that when the agent maximizes the accumulated reward, it also fulfills the task designer's intentions. Recently, significant attention from both academic and industrial researchers has focused on developing reward models that not only align closely with the true objectives but also facilitate policy optimization. In this survey, we provide a comprehensive review of reward modeling techniques within the deep RL literature. We begin by outlining the background and preliminaries in reward modeling. Next, we present an overview of recent reward modeling approaches, categorizing them based on the source, the mechanism, and the learning paradigm. Building on this understanding, we discuss various applications of these reward modeling techniques and review methods for evaluating reward models. Finally, we conclude by highlighting promising research directions in reward modeling. Altogether, this survey includes both established and emerging methods, filling the vacancy of a systematic review of reward models in current literature.
format Preprint
id arxiv_https___arxiv_org_abs_2506_15421
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reward Models in Deep Reinforcement Learning: A Survey
Yu, Rui
Wan, Shenghua
Wang, Yucen
Gao, Chen-Xiao
Gan, Le
Zhang, Zongzhang
Zhan, De-Chuan
Machine Learning
Artificial Intelligence
In reinforcement learning (RL), agents continually interact with the environment and use the feedback to refine their behavior. To guide policy optimization, reward models are introduced as proxies of the desired objectives, such that when the agent maximizes the accumulated reward, it also fulfills the task designer's intentions. Recently, significant attention from both academic and industrial researchers has focused on developing reward models that not only align closely with the true objectives but also facilitate policy optimization. In this survey, we provide a comprehensive review of reward modeling techniques within the deep RL literature. We begin by outlining the background and preliminaries in reward modeling. Next, we present an overview of recent reward modeling approaches, categorizing them based on the source, the mechanism, and the learning paradigm. Building on this understanding, we discuss various applications of these reward modeling techniques and review methods for evaluating reward models. Finally, we conclude by highlighting promising research directions in reward modeling. Altogether, this survey includes both established and emerging methods, filling the vacancy of a systematic review of reward models in current literature.
title Reward Models in Deep Reinforcement Learning: A Survey
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.15421