Proceedings

Efficient Methods for Multi-Objective Decision-Theoretic Planning

Diederik Marijn Roijers

Download BibTeX Cite

Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence. Doctoral Consortium. Pages 4389-4389.

Abstract

In decision-theoretic planning problems, such as (partially observable) Markov decision problems or coordination graphs, agents typically aim to optimize a scalar value function. However, in many real-world problems agents are faced with multiple possibly conflicting objectives. In such multi-objective problems, the value is a vector rather than a scalar, and we need methods that compute a coverage set, i.e., a set of solutions optimal for all possible trade-offs between the objectives. In this project propose new multi-objective planning methods that compute the so-called convex coverage set (CCS): the coverage set for when policies can be stochastic, or the preferences are linear. We show that the CCS has favorable mathematical properties, and is typically much easier to compute that the Pareto front, which is often axiomatically assumed as the solution set for multi-objective decision problems.

Diederik Marijn Roijers. 2015. Efficient Methods for Multi-Objective Decision-Theoretic Planning. In Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-15. IJCAI, 4389–4389. https://ijcai.org/proceedings/2015/642
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards