Papers
1
Total Citations
6
H-Index
1
About
Ruo Wang is a rising researcher in artificial intelligence, specializing in the security and robustness of multi-agent reinforcement learning (MARL) systems. Their work addresses critical vulnerabilities in partially observed environments, where agents must make decisions with incomplete information. Wang’s most notable contribution is the development of SUB-PLAY, a framework for generating adversarial policies that expose weaknesses in MARL deployments—such as drone swarm control, robotic arm collaboration, and multi-target encirclement. This research, published in 2024 and already garnering 6 citations, highlights the urgent need for security measures in real-world AI applications. By systematically revealing how malicious agents can exploit partial observability, Wang’s work provides foundational insights for building more resilient multi-agent systems. Their findings are particularly relevant as MARL expands into safety-critical domains, making Wang a key voice in the emerging field of adversarial machine learning for cooperative AI.
Research Focus
Key Achievements
Top Papers
- 1