Learning to Solve Stochastic Shortest Path Problems

Dierent classes of Stochastic Shortest Path (SSP) problems are considered in literatue. In this paper we'll consider a special case in which edges' costs have probabilistic distribution. We try to learn the expectes cost for each cost and so we learn the shortest path from a node vs to a destination node vd. Our algorithm is somehow like Dijkstra's algorithm, but it just uses local knowledges.