Dana Hughes

Papers

1

Total Citations

2

H-Index

1

About

Dana Hughes is an emerging researcher whose work sits at the intersection of multi-agent reinforcement learning, robotics, and interpretable artificial intelligence. Hughes's most notable contribution, "Concept Learning for Interpretable Multi-Agent Reinforcement Learning" (2023), addresses a critical challenge in modern robotics: as multi-agent systems increasingly operate alongside humans in real-world environments, the opaque nature of deep neural network-based controllers poses significant safety and transparency concerns. By developing a method that incorporates domain expert-defined interpretable concepts into multi-agent policy learning, Hughes bridges the gap between high-performing AI systems and the human oversight necessary for responsible deployment. This work reflects a broader commitment to making complex robotic decision-making legible to non-expert stakeholders — a priority that grows ever more urgent as autonomous systems become embedded in everyday life. Though early in citation accumulation with 2 citations to date, the research targets a timely and consequential problem space. Students and researchers working on human-robot interaction, explainable AI, or cooperative autonomous systems will find Hughes's contributions a valuable entry point into interpretable multi-agent frameworks.

Research Focus

Key Achievements

1
H-Index
1
Papers
2
Total Citations
2
Avg Citations/Paper
🏆 Most Cited Paper
Concept Learning for Interpretable Multi-Agent Reinforcement Learning
2 citations · 2023
📈 Most Prolific Year: 2023 (1 Papers)
🤝 Key Collaborators: 4

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 14 days ago