A practical guide to multi-objective reinforcement learning and planning

Abstract Real-world sequential decision-making tasks are generally complex, requiring trade-offs between multiple, often conflicting, objectives. Despite this, the majority of research in reinforcement learning and decision-theoretic planning either assumes only a single objective, or that multiple objectives can be adequately handled via a simple linear combination. Such approaches may oversimplify the underlying problem and hence produce suboptimal results. This paper serves as a guide to the application of multi-objective methods to difficult problems, and is aimed at researchers who are already familiar with single-objective reinforcement learning and planning methods who wish to adopt a multi-objective perspective on their research, as well as practitioners who encounter multi-objective decision problems in practice. It identifies the factors that may influence the nature of the desired solution, and illustrates by example how these influence the design of multi-objective decision-making systems for complex problems.

Authors

• Conor F. Hayes Cognizant AI Lab
• Roxana Rădulescu Utrecht University
• Diederik M. Roijers

Keywords

• Multi-objective decision making
• Multi-objective reinforcement learning
• Multi-objective planning
• Multi-objective multi-agent systems