Multi-Objective Decision Making

23^rd February 2016, 13:00 Ashton Lecture Theater
Dr. Shimon Whiteson
University of Oxford
Room 407, Wolfson Building,
Parks Road,
Oxford OX1 3QD

Abstract

Many real-world problems require making decisions that involve multiple possibly conflicting objectives. To succeed in such tasks, intelligent agents need algorithms that can efficiently find different ways of balancing the trade-offs that such objectives present. In this talk, I provide an introduction to decision-theoretic planning in the presence of multiple objectives. First, I present an overview of multi-objective decision-theoretic formalisms and show that different assumptions about these problems lead to different solution concepts such as the convex hull and the Pareto front. Then, I present an algorithm developed in my group, called Optimistic Linear Support, which can be combined with a wide range of single-objective solvers to yield an anytime algorithm that efficiently approximates the convex hull, often with bounded error.