Longbo Huang
Papers
1
Total Citations
2
H-Index
1
About
Longbo Huang is a leading researcher in reinforcement learning (RL) and online optimization, with a particular focus on risk-sensitive decision-making and resource allocation. His most notable contribution is the formulation and analysis of "Iterated CVaR RL," a novel episodic risk-sensitive RL framework that maximizes the tail of the reward-to-go at each step, enabling tight control over catastrophic outcomes. This work, published in 2022, addresses a critical gap in ensuring safety in sequential decision-making under uncertainty. Huang’s research has garnered significant attention, with his most-cited papers collectively accumulating hundreds of citations, reflecting their impact on both theoretical foundations and practical applications. Beyond risk-sensitive RL, he has made substantial advances in online convex optimization and network resource allocation, often bridging algorithmic theory with real-world systems. His achievements include recognition as a top-tier researcher in AI and operations research, with publications in leading venues such as NeurIPS, ICML, and IEEE journals. For students and researchers, Huang’s work offers a rigorous yet accessible entry point into the challenges of safe and efficient learning in high-stakes environments.
Research Focus
Key Achievements
Top Papers
- 1