Jinbin Huang
Papers
2
Total Citations
25
H-Index
2
About
Jinbin Huang is a researcher advancing the interpretability and transparency of artificial intelligence, with a primary focus on reinforcement learning (RL). His major contribution lies in developing visual explanation frameworks that demystify the decision-making processes of RL agents. In his most-cited work, "Why? Why not? When? Visual Explanations of Agent Behaviour in Reinforcement Learning" (2022, 21 citations), Huang addresses the critical challenge of the "black box" nature of RL systems used in autonomous driving, robotics, stock trading, and video games. By providing intuitive visual answers to fundamental questions—why an agent chose a particular action, why it rejected alternatives, and when it would act differently—his research makes complex agent behavior accessible to non-expert users, addressing pressing legal and ethical concerns. This work, also presented in a 2021 version (4 citations), demonstrates his commitment to human-centered AI. Huang’s achievements are particularly notable for bridging the gap between advanced machine learning systems and practical human oversight, ensuring that as RL becomes more pervasive, its actions remain understandable and accountable.
Research Focus
Key Achievements
Top Papers
- 1
- 2