A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning

by   Guozheng Ma, et al.
The University of Sydney
Tsinghua University

Visual reinforcement learning (RL), which makes decisions directly from high-dimensional visual inputs, has demonstrated significant potential in various domains. However, deploying visual RL techniques in the real world remains challenging due to their low sample efficiency and large generalization gaps. To tackle these obstacles, data augmentation (DA) has become a widely used technique in visual RL for acquiring sample-efficient and generalizable policies by diversifying the training data. This survey aims to provide a timely and essential review of DA techniques in visual RL in recognition of the thriving development in this field. In particular, we propose a unified framework for analyzing visual RL and understanding the role of DA in it. We then present a principled taxonomy of the existing augmentation techniques used in visual RL and conduct an in-depth discussion on how to better leverage augmented data in different scenarios. Moreover, we report a systematic empirical evaluation of DA-based techniques in visual RL and conclude by highlighting the directions for future research. As the first comprehensive survey of DA in visual RL, this work is expected to offer valuable guidance to this emerging field.


page 4

page 5

page 13

page 15

page 31

page 34

page 38


Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning

Data augmentation (DA) is a crucial technique for enhancing the sample e...

Data Augmentation Approaches for Source Code Models: A Survey

The increasingly popular adoption of source code in many critical tasks ...

A Survey of Automated Data Augmentation Algorithms for Deep Learning-based Image Classication Tasks

In recent years, one of the most popular techniques in the computer visi...

SelectAugment: Hierarchical Deterministic Sample Selection for Data Augmentation

Data augmentation (DA) has been widely investigated to facilitate model ...

Unified State Representation Learning under Data Augmentation

The capacity for rapid domain adaptation is important to increasing the ...

Normalization Enhances Generalization in Visual Reinforcement Learning

Recent advances in visual reinforcement learning (RL) have led to impres...

Structure in Reinforcement Learning: A Survey and Open Problems

Reinforcement Learning (RL), bolstered by the expressive capabilities of...

Please sign up or login with your details

Forgot password? Click here to reset