Shijie Liu
Papers
1
Total Citations
19
H-Index
1
About
Shijie Liu is a prominent researcher in the fields of deep reinforcement learning and continuous control systems, with a focus on advancing autonomous decision-making for real-world applications. Their most-cited work, "An Evaluation of DDPG, TD3, SAC, and PPO: Deep Reinforcement Learning Algorithms for Controlling Continuous System" (2024, 19 citations), provides a comprehensive comparative analysis of four leading algorithms—DDPG, TD3, SAC, and PPO—for managing continuous, analog variables in physical systems. This study is pivotal for developing smooth, intervention-free control policies that enable systems to act appropriately across a range of values, directly impacting robotics, autonomous vehicles, and industrial automation. By systematically evaluating these algorithms, Liu has helped researchers and practitioners select optimal methods for complex, real-time control tasks. Their contributions bridge the gap between theoretical reinforcement learning and practical engineering, offering clear benchmarks for performance and stability. Liu’s work is essential reading for students and engineers seeking to implement robust control in continuous environments, and it underscores their role in shaping the future of intelligent, adaptive systems.
Research Focus
Key Achievements
Top Papers
- 1