Decentralized Multi-agent Exploration with Limited Inter-agent Communications
Hans J. He,Alec Koppel,Amrit Singh Bedi,Daniel J. Stilwell,Mazen Farhood,Benjamin Biggs,Hans J. He,Alec Koppel,Amrit Singh Bedi,Daniel J. Stilwell,Mazen Farhood,Benjamin Biggs
We consider the problem of decentralized multiagent environmental learning through maximizing the joint information gain among a team of agents. Inspired by subsea applications where bandwidth is severely limited, we explicitly consider the challenge of restricted communication between agents. The environment is modeled as a Gaussian process (GP), and the global information gain maximization probl...
