Bao-Song Deng

Towards Transparent Multi-Agent Autonomous Systems Through Principled Multi-Source Knowledge Distillation

Many real-world robotic applications can be formulated as Multi-Agent Path-Finding (MAPF) problems and approximated using Multi-Agent Reinforcement Learning (MARL) algorithms. However, the opaque nature of the blackbox neural network models employed by MARL algorithms has impeded their widespread ad