A Practical Guide to Multi-Objective Reinforcement Learning and Planning
It targets researchers and practitioners in AI/ML facing multi-objective decision problems, offering incremental guidance rather than new algorithms.
The paper addresses the oversimplification in reinforcement learning and planning by single-objective or linear combination approaches, providing a practical guide for applying multi-objective methods to complex decision-making problems with trade-offs.
Real-world 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.