Multi-Agent Reinforcement Learning
Cooperative decision-making and coordination among multiple learning agents.
Artificial Intelligence · Southeast University
Jiarui Cao
I am an undergraduate student at the School of Artificial Intelligence, Southeast University.
My research focuses on multi-agent reinforcement learning, particularly agent communication, partial observability, belief modeling, and adaptive collaboration with unfamiliar teammates.
Research Interests
I study how intelligent agents can communicate, reason about missing information, and cooperate robustly in partially observable environments.
Agent Communication
Reliable information exchange under limited visibility and communication loss.
Teammate Modeling
Learning decision-relevant representations of unfamiliar collaborators.
Selected Work
Selected research projects in cooperative multi-agent intelligence.
BeliefHub architecture. Click the figure to view it at full size.
Research Project
BeliefHub
Visibility-Aware Belief Reconstruction for Communication-Robust Multi-Agent Reinforcement Learning
BeliefHub investigates recurrent entity-belief reconstruction and reliability-aware information fusion for robust cooperative decision-making under limited visibility and packet loss.
View project on GitHub →Education
Undergraduate
Southeast University
School of Artificial Intelligence
Nanjing, China