A Practical Guide to Multi-Objective Reinforcement Learning and Planning

TL;DR

This paper provides a comprehensive guide for applying multi-objective reinforcement learning and planning techniques to complex decision-making problems involving conflicting objectives, highlighting factors influencing solution design.

Contribution

It offers practical insights and examples for researchers and practitioners to adopt multi-objective methods beyond simple linear combinations in complex tasks.

Findings

Highlights importance of factors influencing multi-objective solutions

Illustrates design considerations for multi-objective decision systems

Guides adaptation of single-objective methods to multi-objective contexts

Abstract

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.