Exploring and exploiting routing opportunities in wireless ad-hoc networks

In this paper, d-AdaptOR, a distributed opportunistic routing scheme for multi-hop wireless ad-hoc networks is proposed. The proposed scheme utilizes a reinforcement learning framework to achieve the optimal performance adaptively even in the absence of reliable knowledge about channel statistics and network model. The scheme extends an earlier proposed scheme which relied on centralized computation. In contrast, d-AdaptOR operates solely based on local information and coordination with other neighboring nodes via network message passing while achieving optimality with respect to an expected average per packet reward criterion.