Multi-Agent Reinforcement Learning (MARL) algorithms suffer from slow convergence and even divergence, especially in large-scale systems. In this work, we develop a supervision fr...
Chongjie Zhang, Sherief Abdallah, Victor R. Lesser
— To be acceptable to human drivers, the motion of an intelligent robotic wheelchair must be more than just collision-free: it must be graceful. We define graceful motion as bei...
This paper explores strategies for slowing the onset of convergence in an evolving population of agents. The strategies include the emergent maintenance of separate agent sub-popul...
TCP Slow Start exponentially increases the congestion window size to detect the proper congestion window for a network path. This often results in significant packet loss, while ...
This paper presents a protocol for packet switched optical LANs using a star topology. The key element in this network is the use of an intelligent hub, which controls the traffic...