Aishan Liu
Papers
4
Total Citations
25
H-Index
3
About
Aishan Liu is a leading researcher at the intersection of imitation learning and multi-agent reinforcement learning (MARL), with a focus on robustness and adversarial security. His work fundamentally advances our understanding of how autonomous agents learn from observation—a critical capability for real-world deployment where expert demonstrations are often incomplete. In his highly cited 2021 paper, Liu established the theoretical equivalence between imitation learning from observation (LfO) and from demonstration (LfD), proving that LfO can match LfD’s performance under guaranteed conditions, thereby enabling safer and more practical agent training. More recently, Liu has pioneered the study of vulnerabilities in cooperative multi-agent systems. His 2023–2025 series on adversarial minority influence (accumulating over 17 citations) reveals how a small subset of compromised agents can destabilize entire cooperative teams, exposing critical security gaps in MARL before real-world deployment. By challenging white-box assumptions and probing worst-case performance, Liu’s work provides both foundational theory and actionable insights for building resilient multi-agent systems. His research is essential reading for anyone working on trustworthy AI, robotics, or autonomous coordination.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4