Chris Bryan
Papers
2
Total Citations
25
H-Index
2
About
Chris Bryan is a leading researcher at the intersection of visualization, human-computer interaction, and explainable AI. His work focuses on making complex, black-box machine learning systems—particularly reinforcement learning (RL) agents—transparent and interpretable to non-expert users. Bryan’s most cited paper, “Why? Why not? When? Visual Explanations of Agent Behaviour in Reinforcement Learning” (2022, 21 citations), introduces a novel framework that generates visual explanations to answer critical questions about an agent’s decisions: why it chose a particular action, why it avoided another, and when it might change its behavior. This work directly addresses the growing legal and ethical challenges in deploying RL in high-stakes domains like autonomous driving, robotics, and stock trading. By bridging the gap between technical AI performance and human understanding, Bryan’s contributions empower stakeholders to trust, debug, and improve intelligent systems. His research is pivotal for students and practitioners seeking to build safer, more accountable AI, and his innovative approach to visual storytelling in data science continues to shape how we interact with and interpret autonomous agents.
Research Focus
Key Achievements
Top Papers
- 1
- 2