Visual reinforcement learning (RL), which makes decisions directly from high-dimensional
visual inputs, has demonstrated significant potential in various domains. However …

As the challenges in autonomous driving become more complex and changing, traditional
methods are struggling to cope. As a result, artificial intelligence (AI) techniques have …

Plasticity, the ability of a neural network to evolve with new data, is crucial for high-
performance and sample-efficient visual reinforcement learning (VRL). Although methods …

Despite the remarkable progress made in visual reinforcement learning (RL) in recent years,
sample inefficiency remains a major challenge. Many existing approaches attempt to …

Recent advances in visual reinforcement learning (RL) have led to impressive success in
handling complex tasks. However, these methods have demonstrated limited generalization …

Learning effective visual representations is crucial in open-world environments where
agents encounter diverse and unstructured observations. This ability enables agents to …

The inherent generalization problem in reinforcement learning (RL) is exacerbated when
dealing with high-dimensional visual input. Data augmentation is a promising method to …

Abstract In visual Reinforcement Learning (RL), one of the key problems is how to learn
policies, which can be generalized to unseen environments. Recently, saliency guidance …

In reinforcement learning (RL), learning directly from pixels, is commonly known as vision-
based RL. Effective state representations are crucial for high performance in vision-based …

In visual Reinforcement Learning (RL), learning from pixel-based observations poses
significant challenges on sample efficiency, primarily due to the complexity of extracting …