A distributed reinforcement learning approach to mission survivability in tactical MANETs

In this paper we present an ongoing research to develop a distributed reinforcement learning approach for mission survivability that combines two basic strategies for mission resilience: a) mission decomposition and distribution with replication of critical components, and b) differential task allocation based on estimated level of threat. Level of threat is estimated from a locally perceived attack, or the possibility of an attack, based on threat information that is shared between similar nodes.