Brief Bio (Wen-Zhang Liu, 柳文章)
Presently, I serve as a research scientist at the School of Artificial Intelligence, Anhui University. Prior to this role, I successfully completed my Ph.D. research at the School of Automation, Southeast University. During that period, I also engaged in an internship at Peng Cheng Laboratory. My research interests include deep reinforcement learning, multi-agent reinforcement learning, transfer learning, and robot learning, etc. My research goal is to develop versatile agents endowed with general intelligence.
🔥 News
-
2024.04.01: 🎉🎉 We have created WeChat official account for XuanCe, named “玄策 RLlib”. Welcome to follow it!
-
2023.12.25: 🎉🎉 Merry Christmas! The paper of XuanCe is online: https://arxiv.org/abs/2312.16248.
-
2023.05.22: 🎉🎉 We have released XuanCe: https://github.com/agi-brain/xuance on GitHub, an open-source deep reinforcement learning library. Welcome to star and use!
📃 Publications
-
Xiang Cao, Wenzhang Liu, Lu Ren: Underwater target capture based on heterogeneous unmanned system collaboration. IEEE Transactions on Intelligent Vehicles (2024) [BibTex]
-
Wenzhang Liu, Wenzhe Cai, Kun Jiang, Guangran Cheng, Yuanda Wang, Jiawei Wang, Jingyu Cao, Lele Xu, Chaoxu Mu, Changyin Sun: XuanCe: A comprehensive and unified deep reinforcement learning library. arXiv:2312.16248 (2023) [Paper] [BibTex] [Code]
-
Kun Jiang, Wenzhang Liu, Yuanda Wang, Lu Dong, Changyin Sun: Credit assignment in heterogeneous multi-agent reinforcement learning for fully cooperative tasks. Appl. Intell. 53(23): 29205-29222 (2023) [Paper] [BibTex]
-
Yuewen Sun, Wenzhang Liu, Changyin Sun. Causality in reinforcement learning control: The state of the art and prospects. Acta Automatica Sinica. 49(3): 661−677 (2023) doi: 10.16383/j.aas.c220823 [Paper] [BibTex]
-
Yuanda Wang, Wenzhang Liu, Jian Liu, Changyin Sun: Cooperative USV–UAV marine search and rescue with visual navigation and reinforcement learning-based control. ISA transactions. 137: 222-235 (2023) [Paper] [BibTex]
-
Wenzhang Liu, Lu Dong, Dan Niu, Changyin Sun: Efficient exploration for multi-agent reinforcement learning via transferable successor features. IEEE CAA J. Autom. Sinica 9(9): 1673-1686 (2022) [Paper] [BibTex] [Code] [Videos]
-
Wenzhang Liu, Lu Dong, Jian Liu, Changyin Sun: Knowledge transfer in multi-agent reinforcement learning with incremental number of agents. Journal of systems engineering and electronics. 33(2): 447-460 (2022) [Paper] [BibTex] [Code]
-
Changyin Sun, Wenzhang Liu, Lu Dong: Reinforcement learning with task decomposition for cooperative multiagent systems. IEEE Trans. Neural Networks Learn. Syst. 32(5): 2054-2065 (2021) [Paper] [BibTex]
-
Yuewen Sun, Xin Yuan, Wenzhang Liu, Changyin Sun: Model-based reinforcement learning via proximal policy optimization. Chinese Automation Congress (CAC) 2019: 4736-4740 [Paper] [BibTex]
-
Wenzhang Liu, Haiqin Yang, Yuewen Sun, Changyin Sun: A broad neural network structure for class incremental learning. Advances in Neural Networks–ISNN 2018: 15th International Symposium on Neural Networks: 229-238 [Paper] [BibTex]
🔏 CN Patens
-
任璐,邵逸凡,李明轩,柳文章,郑烨. 一种雾天场景下的海上小目标航拍图像识别模型训练方法[P]. 安徽省:CN202410078638.0,2024-04-16.
-
李晓峰,孙长银,柳文章,任璐. 一种非线性网络控制系统多目标协同最优控制方法[P]. 安徽省:CN202311488926.5,2024-02-23.
-
任璐,冯士营,柳文章,等. 一种基于深度强化学习和PID控制器的无人机导航方法[P]. 安徽省:CN202311707956.0,2024-01-12.
-
柳文章,舒宝林,任璐,孙长银. 一种基于强化学习的任意角度倒立摆模型训练方法[P]. 安徽省:CN202311615603.8,2024-02-23.
-
柳文章,柯亚男,任璐,孙长银. 基于近端策略优化的多无人艇深度强化学习协同导航方法[P]. 安徽省:CN202311452155.4,2024-02-06.
-
孙长银,柳文章,穆朝絮,任璐,施卓然. 一种基于统一AI框架的深度强化学习智能决策平台[P]. 安徽省:CN202311338634.3,2024-01-19.
-
任璐,李浩,柳文章,宋坤. 一种基于有偏选择池化的图像分类方法[P]. 安徽省:CN202310552011.X,2024-04-05.
-
王轶默,刘剑,许一航,薛磊,柳文章. 一种基于特征共享的自学习迁移方法[P]. 江苏省:CN202110362608.9,2024-03-26.
🏅 Honors and Awards
- 2022.08, Kun Jiang, Jingyu Cao, Wenzhang Liu and Lu Dong. The 2022 RoboMaster Sim2Real Challenge Third Prize, 2022 IEEE Conference on Games. (Organized by IEEE Computational Intelligence Society)
🎓 Educations
-
2016.08 - 2021.12, Doctor, School of Automation, Southeast University, Nanjing, P.R.China.
-
2012.08 - 2016.06, Bachelor, Department of Control Science and Engineering, Jilin University, Changchun, P.R.China.
🎙️ Invited Talks
-
2023.11.11, 从深度强化学习到多智能体强化学习:算法、结构、机遇和挑战, 第十七届吉林省科协青年科学家论坛——AI创新与发展,(会议主办方:吉林省科学技术协会).
-
2018.10.18, A broad neural network structure for class incremental learning, 第二十届海峡两岸信息技术研讨会(CSIT2018),(会议主办方:东南大学).
💻 Internships
-
2021.10 - 2022.05, Peng Cheng Laboratory, Shenzhen, China.
-
2017.12 - 2018.03, Department of Computer Science, Hang Seng University of Hong Kong, China.
🇺🇳 Research Group
Leadership
- Changyin Sun, professor, vice-principal, School of Artificial Intelligence, Anhui University.
Collaborators
- Lu Ren, associate professor, School of Artificial Intelligence, Anhui University.
Graduate Students
-
Baolin Shu, Grade 2 (Sep 2022-), thesis topic: deep reinforcement learning model compressing with policy distillations.
-
Chen Wang, Grade 2 (Sep 2022-), thesis topic: safe reinforcement learning.
-
Haoyu Feng, Grade 2 (Sep 2022-), thesis topic: multi-agent pursuit-prey games.
-
Keke Yang, Grade 2 (Sep 2022-), thesis topic: drones control with deep reinforcement learning.
-
Lianjun Jin, Grade 2 (Sep 2022-), thesis topic: deep reinforcement learning with continuous tasks.
-
Yanan Ke, Grade 2 (Sep 2022-), thesis topic: multi-agent reinforcement learning.
-
Zelong Fang, Grade 2 (Sep 2022-), thesis topic: drones control with deep reinforcement learning.
-
Zhuoran Shi, Grade 2 (Sep 2022-), thesis topic: drones control with deep reinforcement learning.
-
Wanyi Yao, Grade 1 (Sep 2023-).
-
Jianhua Lu, Grade 1 (Sep 2023-).
Undergraduate Students
- Minghui Lu, Yuhang Teng, Chuchu Yan, Junjie He, Qihua Wang, Wentao Wei, Ye Zheng, Yiming Guan, Yangyang Song, Yujie Ying, Zhen Wang, Zhouhui Chen.
📬 Contact
I’m reachable via email at wzliu at ahu dot edu dot cn.
My research office: Room D205, Building H, Materials Science Building (材料科学大楼H座D205室).
Address: No.111 Jiulong Road, Hefei, Anhui, China (230601) (安徽省合肥市经济技术开发区九龙路111号,邮编:230601).