Welcome to Haoyuan Jiang’s Personal Homepage!
Now, I am a senior algorithm engineer at Baidu Inc. Before that, i was a researcher at Sensetime. My research interest includes Reinforcement Learning, AI Agents and Embodied AI, driven by a desire to contribute to building AGI algorithms. I worked closely with Prof. Ziyue Li at the University of Cologne and Researcher Hangyu Mao.
In my experiences, I have been investigating how to enable autonomous agents to learn, make decisions in complex environments, and apply them in reality. This includes developing new reinforcement learning algorithms that allow agents to cooperate, easily adapt to new environments and meet industry requirements.
If you are interested with my experience or research. Please feel free to contact with me!
🔥 News
- 2024.05: 🎉🎉 One paper is accepted by KDD 2024!
- 2024.04: 🎉🎉 One first-author paper is accepted by IJCAI 2024!
- 2024.02: 🎉🎉 One first-author paper is accepted by IEEE TITS!
- 2023.12: 🎉🎉 One paper is accepted by AAMAS 2024!
📝 Publications
Haoyuan Jiang, Ziyue Li, Hua Wei, Xuantang Xiong, Jingqing Ruan, Jiaming Lu, Hangyu Mao, Rui Zhao.
- We propose a reinforcement learning algorithm for the multiple traffic signals control field that has good generalization and transferability while achieving SOTA performance.
- code
A General Scenario-Agnostic Reinforcement Learning for Traffic Signal Control
Haoyuan Jiang, Ziyue Li, Zhishuai Li, Lei Bai, Hangyu Mao, Wolfgang Ketter, Rui Zhao.
- We proposed a reinforcement learning algorithm for the traffic signal control field, which can easily cope with different scenarios and various types of intersections. Through training in large-scale scenarios, we found that the performance has been significantly improved and has strong generalization.
- code
- CoSLight: Co-optimizing Collaborator Selection and Decision-making to Enhance Traffic Signal Control
ACM SIGKDD Conference on Knowledge Discovery and Data Mining(KDD), in Barcelona, Spain, 2024.
Jingqing Ruan, Ziyue Li, Hua Wei, Haoyuan Jiang, Jiaming Lu, Xuantang Xiong, Hangyu Mao, Rui Zhao. \ - DuaLight: Enhancing Traffic Signal Control by Leveraging Scenario-Specific and Scenario-Shared Knowledge
International Conference on Autonomous Agents and Multi-Agent Systems(AAMAS), in Auckland, New Zealand, 2024. (Oral)
Jiaming Lu, Jingqing Ruan, Haoyuan Jiang, Ziyue Li, Hangyu Mao, Rui Zhao. \
🧑🎨 Preprint
- GuideLight: “Industrial Solution” Guidance for More Practical Traffic Signal Control Agents. Haoyuan Jiang, Xuantang Xiong, Ziyue Li, Hangyu Mao, Guanghu Sui, Jingqing Ruan, Yuheng Cheng, Hua Wei, Wolfgang Ketter, Rui Zhao.
📖 Educations
- 2017.09 - 2019.06, Master in Software Engineering, Zhejiang University.
💻 Work and Research Experience
- 2023.09 - Present, Baidu Inc., China.
- 2019.07 - 2023.09, Sensetime Research, China.
🌠 Services
Program Committee Member or Reviewer:
- International Conference on Autonomous Agents and Multiagent Systems (AAMAS)
🎖 Honors and Awards
- 2017, 14th National Graduate Mathematical Modeling Competition, Second Prize.
- 2017, Honor Student in IBM Innovation Bootcamp.
- 2018, 11th China College Students’ Entrepreneurship Competition, Bronze Award in Zhejiang Province.
- 2022, IJCAI 2022 - Neural MMO Challenge, Bronze Tier Award.
- 2022, Outstanding Individual of the Year in Sensetime SCG R&D Department.