收藏切换
Visual Reinforcement Learning Representation Optimization Based on Memory Augmentation and Environment Disentanglement
收藏切换
Donghong Xu, Shilong Wu*
Journal of Computer Research and Development | 2026, 63(5) : 1273 - 1289
Less
收藏切换
Journal of Computer Research and Development | 2026, 63(5): 1273-1289
• Artificial Intelligence •
Visual Reinforcement Learning Representation Optimization Based on Memory Augmentation and Environment Disentanglement
Full
Donghong Xu, Shilong Wu*
Affiliations
  • School of Computer Science and Technology/ School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, Jiangsu 221116
  • Mine Digitization Engineering Research Center of the Ministry of Education (China University of Mining and Technology), Xuzhou, Jiangsu 221116
  • Jiangsu Provincial Industrial Technology Engineering Center for Intelligent Sensing and Emergency loT in Underground Space(China University of Mining and Technology), Xuzhou, Jiangsu 221116
  • born in 1977. PhD, associate professor, master supervisor. His main research interests include deep reinforcement learning, visual reinforcement learning, cloud computing, and large model

    born in 2000. Master candidate. His main research interests include deep reinforcement learning and visual reinforcement learning

About Author:

born in 1977. PhD, associate professor, master supervisor. His main research interests include deep reinforcement learning, visual reinforcement learning, cloud computing, and large model

born in 2000. Master candidate. His main research interests include deep reinforcement learning and visual reinforcement learning

Published: 2026-05-01 doi: 10.7544/issn1000-1239.202550320
Outline
收藏切换

Visual reinforcement learning has demonstrated enormous potential across a wide range of domains. However, current algorithms still face two core challenges: insufficient generalization capability and low sample efficiency. Due to the limited availability of training data and the diversity and complexity of environments, reinforcement learning agents often become overly reliant on specific features present in the training settings, which hampers their ability to adapt to novel environments. Even minor environmental changes can induce significant alterations in image pixels, thereby affecting the latent representations learned by the agents and ultimately causing their policies to fail. To develop robust representations, we introduce the environment disentangled representation learning (EDRL) algorithm for visual reinforcement learning. It employs a self-supervised framework to extract environment-invariant features, thereby significantly enhancing the agent’s generalization and sample efficiency. Firstly, by employing periodic data augmentation and integrating historical observations, the method simulates complex environmental changes and expands the effective observation range, thus reducing policy biases caused by training instability. Secondly, robust, environment-invariant features are obtained by disentangling latent features and isolating them through reconstruction. Finally, by predicting the changes in representations across time steps and incorporating a dynamic consistency loss, the approach ensures the consistency and robustness of the representations. Experimental results demonstrate the effectiveness of EDRL, as validated on the DMControl generalization benchmark (DMControl-GB) and the distracting control suite (DistractingCS). The results indicate that, compared with state-of-the-art methods, EDRL achieves an average performance improvement of over 15% in complex scenarios on DMControl-GB and over 20% in highly distracting environments on DistractingCS.

visual reinforcement learning  /  representation disentanglement  /  data augmentation  /  generalization  /  self-supervised learning
徐东红, 武世龙. 基于记忆增强和环境解耦的视觉强化学习表征优化. 计算机研究与发展, 2026 , 63 (5) : 1273 -1289 . DOI: 10.7544/issn1000-1239.202550320
Donghong Xu, Shilong Wu. Visual Reinforcement Learning Representation Optimization Based on Memory Augmentation and Environment Disentanglement[J]. Journal of Computer Research and Development, 2026 , 63 (5) : 1273 -1289 . DOI: 10.7544/issn1000-1239.202550320
Year 2026 volume 63 Issue 5
80
37
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202550320
  • Receive Date:2025-05-15
  • Online Date:2026-11-17
  • Published:2026-05-01
Article Data
Affiliations
History
  • Received:2025-05-15
  • Revised:2025-12-15
  • Accepted:2026-01-07
Affiliations
    School of Computer Science and Technology/ School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, Jiangsu 221116
    Mine Digitization Engineering Research Center of the Ministry of Education (China University of Mining and Technology), Xuzhou, Jiangsu 221116
    Jiangsu Provincial Industrial Technology Engineering Center for Intelligent Sensing and Emergency loT in Underground Space(China University of Mining and Technology), Xuzhou, Jiangsu 221116
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202550320
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT