Planning in the Presence of Cost Functions Controlled by an Adversary
journal contributionposted on 01.10.1993 by H. Brendan McMahan, Geoffrey J. Gordon, Avrim Blum
Any type of content formally published in an academic journal, usually following a peer-review process.
We investigate methods for planning in a Markov Decision Process where the cost function is chosen by an adversary after we fix our policy. As a running example, we consider a robot path planning problem where costs are influenced by sensors that an adversary places in the environment. We formulate the problem as a zero-sum matrix game where rows correspond to deterministic policies for the planning player and columns correspond to cost vectors the adversary can select. For a fixed cost vector, fast algorithms (such as value iteration) are available for solving MDPs. We develop efficient algorithms for matrix games where such best response oracles exist. We show that for our path planning problem these algorithms are at least an order of magnitude faster than direct solution of the linear programming formulation.