Zheng‐Yao Jiang
Papers
1
Total Citations
3
H-Index
1
About
Zheng-Yao Jiang is a researcher advancing the frontier of reinforcement learning, with a particular focus on planning-based methods and scalable decision-making. His most cited work, "Efficient Planning in a Compact Latent Action Space" (2022, 3 citations), addresses a critical bottleneck in reinforcement learning: the computational overhead of planning in high-dimensional action spaces. Jiang’s key contribution lies in demonstrating how planning can be made efficient by compressing action spaces into compact latent representations, enabling strong performance in tasks that were previously computationally prohibitive. This work bridges the gap between discrete and continuous control, offering a pathway to scalable, real-time planning for complex environments. While early in his citation impact, Jiang’s research is notable for tackling a fundamental challenge in modern AI—how to combine the deliberative power of planning with the efficiency required for high-dimensional, real-world applications. His approach has implications for robotics, autonomous systems, and any domain requiring fast, intelligent decision-making under constraints. Jiang’s work represents a promising step toward more practical and powerful reinforcement learning agents.
Research Focus
Key Achievements
Top Papers
- 1Efficient Planning in a Compact Latent Action Space3 citations · 2022