Linglong Kong
Papers
1
Total Citations
4
H-Index
1
About
Linglong Kong is a leading researcher in distributional reinforcement learning, with a focus on advancing exploration strategies and decision-making under uncertainty. Their most notable contribution is the Quantile Option Architecture (QUOTA), introduced in a 2018 paper, which leverages quantiles of value distributions—rather than just their means—to guide exploration in RL. This work provides a novel dimension for exploration, enabling more robust and efficient learning in complex environments. With over 4 citations to this key paper, Kong’s research has influenced the growing field of distributional RL, particularly in how agents can quantify and act on risk and uncertainty. Their work bridges theoretical insights with practical algorithm design, making significant strides in improving sample efficiency and policy performance. Kong’s contributions are essential reading for students and researchers interested in the intersection of reinforcement learning, quantile-based methods, and exploration.
Research Focus
Key Achievements
Top Papers
- 1QUOTA: The Quantile Option Architecture for Reinforcement Learning4 citations · 2018