Jiahao Zheng
Papers
1
Total Citations
12
H-Index
1
About
Jiahao Zheng is a leading researcher in cloud-native deep reinforcement learning (DRL), with a focus on scalable and elastic frameworks that bridge the gap between algorithmic innovation and real-world deployment. His most cited work, "ElegantRL-Podracer: Scalable and Elastic Library for Cloud-Native Deep Reinforcement Learning" (2021, 12 citations), addresses a critical bottleneck in DRL: the high cost of data collection through agent-environment interactions. By designing a library that leverages cloud-native principles—enabling dynamic scaling, resource elasticity, and efficient parallelization—Zheng’s contribution dramatically reduces the computational and financial barriers to training complex DRL models. This work has been pivotal for applications ranging from game playing to robotic control, where real-time, cost-effective learning is essential. Zheng’s research underscores the importance of infrastructure in advancing AI, making DRL more accessible for complex, real-world tasks. His achievements highlight a forward-thinking approach to system-level optimization, positioning him as a key figure in the evolution of practical, scalable reinforcement learning.
Research Focus
Key Achievements
Top Papers
- 1