Yingcai Wu
Papers
1
Total Citations
6
H-Index
1
About
Yingcai Wu is a rising researcher in artificial intelligence, with a primary focus on the security and robustness of multi-agent reinforcement learning (MARL) systems. His work addresses critical vulnerabilities in partially observable environments, where agents must make decisions with incomplete information. His most-cited paper, “SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems” (2024, 6 citations), introduces a novel framework for generating adversarial policies that can exploit weaknesses in MARL deployments. This research is particularly significant for real-world applications such as drone swarm control, robotic arm collaboration, and multi-target encirclement, where security threats could have severe consequences. By exposing these vulnerabilities, Wu’s work lays the foundation for developing more resilient and trustworthy multi-agent systems. His contributions are timely, given the rapid expansion of MARL into safety-critical domains. As an early-career scholar, Wu’s research is already drawing attention for its practical implications in AI safety, positioning him as a promising voice in the intersection of reinforcement learning and cybersecurity.
Research Focus
Key Achievements
Top Papers
- 1