Ph.D. at The university of Electro-Communications, China
Zhiqiang He is an emerging researcher specializing in reinforcement learning and artificial intelligence (AI), with a focus on developing and optimizing control algorithms for complex systems. He has made significant contributions to both academic research and industrial applications, demonstrating expertise in designing innovative AI solutions for real-world problems. His educational background in control science and engineering, combined with practical experiences at leading tech companies, has shaped his career and led to several impactful publications in renowned journals. Zhiqiang’s accomplishments, recognized through various academic awards and industry achievements, make him a strong candidate for the “Best Researcher Award.”
Profile
ORCID
Education
Zhiqiang pursued his Master of Science in Control Science and Engineering at Northeastern University (NEU), Shenyang, China, from September 2019 to June 2022, where he maintained a commendable GPA of 3.29/4. During his master’s program, he specialized in the development of reinforcement learning algorithms, which formed the cornerstone of his research. Prior to this, he earned his Bachelor of Science in Automation at East China Jiaotong University (ECJTU), Nanchang, China, from September 2015 to June 2019, with a GPA of 3.42/4. His undergraduate studies laid a strong foundation in automation and control systems, providing the technical skills and knowledge that fueled his passion for AI and intelligent decision-making.
Experience
Throughout his academic journey, Zhiqiang actively engaged in research and industry roles that enriched his experience in the field of AI. He served as a team leader at the Institute of Deep Learning and Advanced Intelligent Decision-Making at NEU, where he worked on the development of reinforcement learning algorithms. Leading projects from September 2020 to June 2021, he conducted research on model-based reinforcement learning, optimized algorithm performance, and supervised students in their projects. Additionally, his early experience as a team leader at the Jiangxi Province Advanced Control and Key Optimization Laboratory involved applying reinforcement learning to control problems from 2016 to 2019, where he gained hands-on skills in analyzing system behaviors and establishing Markov Decision Process (MDP) models.
In the industry, Zhiqiang took on roles that deepened his technical expertise. He was an intern at Baidu, Beijing, China, where he pioneered the development of the Expert Data-Assisted Multi-Agent Proximal Policy Optimization (EDA-MAPPO) algorithm, an innovative approach to multi-agent cooperative adversarial AI. Later, as a reinforcement learning algorithms engineer at InspirAI in Hangzhou, he led the development of AI strategies for popular card games, showcasing his ability to apply AI solutions to commercial projects and enhance algorithmic performance.
Research Interest
Zhiqiang’s research interests are centered on reinforcement learning, AI, and control systems. He focuses on designing algorithms that improve the efficiency and accuracy of AI models in decision-making tasks. His work involves exploring new methods for multi-agent reinforcement learning, optimizing algorithms for real-time applications, and addressing challenges in intelligent control. By bridging theoretical research with practical applications, he aims to push the boundaries of AI, making it more adaptable and applicable to various industries. His dedication to advancing reinforcement learning techniques aligns with the future trajectory of AI research, where automation and intelligent decision-making are key drivers of innovation.
Awards
Zhiqiang has received recognition for his academic excellence and research contributions throughout his career. He was honored as an “Outstanding Graduate” by East China Jiaotong University in 2019, acknowledging his academic achievements and leadership potential. In addition, he secured the Third Prize in the 15th “Challenge Cup” Jiangxi Division in 2017 and the Second Prize in the International Mathematical Modeling Competition for American College Students in 2018, demonstrating his problem-solving skills and competitive spirit. His active engagement in professional development is further highlighted by his certifications in network technology and programming languages, which add to his multidisciplinary skill set.
Publications
He Z, Qiu W, Zhao W, et al. Understanding World Models through Multi-Step Pruning Policy via Reinforcement Learning. Information Sciences, 2024: 121361. – Cited by 32 articles.
Chen P, He Z, Chen C, et al. Control strategy of speed servo systems based on deep reinforcement learning. Algorithms, 2018, 11(5): 65. – Cited by 15 articles.
Wang J, Zhang L, He Z, et al. Erlang planning network: An iterative model-based reinforcement learning with multi-perspective. Pattern Recognition, 2022, 128: 108668. – Cited by 27 articles.
Zhang L, He Z, Zhao Y, et al. Reinforcement Learning-based Control of Robotic Manipulators. Journal of Robotics, 2023, 12(3): 112-121. – Cited by 19 articles.
He Z, Zhao W, Zhang L, et al. Multi-Agent Deep Reinforcement Learning in Dynamic Environments. Artificial Intelligence Review, 2022, 55(2): 456-472. – Cited by 24 articles.
Chen C, He Z, Qiu W, et al. Optimal Control for Nonlinear Systems Using Reinforcement Learning. Control Theory and Applications, 2021, 59(4): 553-566. – Cited by 18 articles.
Conclusion
Zhiqiang He’s contributions to AI and reinforcement learning, coupled with his practical experience and research output, position him as a promising researcher in the field. His work not only advances the academic understanding of intelligent control but also finds applications in industry, where AI solutions are critical to technological development. By consistently pushing for excellence in his projects, he demonstrates qualities that make him a deserving candidate for the “Best Researcher Award.” His trajectory reflects a commitment to innovation, making him an asset to the research community and a potential leader in future AI advancements.