Hayes, C. F. , Radulescu, R. , Bargiacchi, E. , Källström, J., Macfarlane, M. , Reymond, M. , Verstraeten, T. , Zintgraf, L., Dazeley, R., Heintz, F., Howley, E., Irissappane, A. A., Mannion, P. , Nowe, A. , De Oliveira Ramos, G., Restelli, M., Vamplew, P. , & Roijers, D. M. (2022). A Practical Guide to Multi-Objective Reinforcement Learning and Planning . Autonomous Agents and Multi-Agent Systems , 36 (1), [26].

@article{9f4f075da2a346aea7254773e228e8e5,
title = " 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. " ,
author = " Hayes, {Conor F.} and Roxana Radulescu and Eugenio Bargiacchi and Johan K{ " a}llstr{ " o}m and Matthew Macfarlane and Mathieu Reymond and Timothy Verstraeten and Luisa Zintgraf and Richard Dazeley and Fredrik Heintz and Enda Howley and Irissappane, {Athirai A.} and Patrick Mannion and Ann Nowe and {De Oliveira Ramos}, Gabriel and Marcello Restelli and Peter Vamplew and Roijers, {Diederik M.} " ,
note = " Funding Information: This research was supported by funding from the Fonds voor Wetenschappelijk Onderzoek (FWO) through the grant of Eugenio Bargiacchi (#1SA2820N), and by funding from the Flemish Government under the “Onderzoeksprogramma Artifici{ " e}le Intelligentie (AI) Vlaanderen” for Diederik M. Roijers and Ann Now{'e}. Roxana R{u a}dulescu was partially supported through the FWO iBOF/21/027 project “DESCARTES”. Conor F. Hayes is funded by the National University of Ireland Galway Hardiman Scholarship. Gabriel Ramos was partially supported by FAPERGS (grant 19/2551-0001277-2) and FAPESP (grant 2020/05165-1). Johan K{ " a}llstr{ " o}m and Fredrik Heintz were partially supported by the Swedish Governmental Agency for Innovation Systems (grant NFFP7/2017-04885), and the Wallenberg Artificial Intelligence, Autonomous Systems and Software Program (WASP) funded by the Knut and Alice Wallenberg Foundation. Matthew Macfarlane was funded by LIFT-project 019.011 which is partly financed by the Dutch Research Council (NWO). Luisa Zintgraf is supported by the 2017 Microsoft Research PhD Scholarship Program, and the 2020 Microsoft Research EMEA PhD Award. Publisher Copyright: { extcopyright} 2022, The Author(s). " ,
year = " 2022 " ,
month = apr,
day = " 13 " ,
doi = " 10.1007/s10458-022-09552-y " ,
language = " English " ,
volume = " 36 " ,
journal = " Autonomous Agents and Multi-Agent Systems " ,
issn = " 1387-2532 " ,
publisher = " Springer Netherlands " ,
number = " 1 " ,
}