A Brief Guide to Multi-Objective Reinforcement Learning and Planning: JAAMAS Track

Conor F. Hayes, Roxana Radulescu, Eugenio Bargiacchi, Johan Källström, Matthew Macfarlane, Mathieu Reymond, Timothy Verstraeten, Luisa Zintgraf, Richard Dazeley, Fredrik Heintz, Enda Howley, Athirai A. Irissappane, Patrick Mannion, Ann Nowe, Gabriel De Oliveira Ramos, Marcello Restelli, Peter Vamplew, Diederik M. Roijers

Onderzoeksoutput: Conference paperResearch

Samenvatting

Real-world sequential decision-making tasks are usually complex, and require trade-offs between multiple -- often conflicting -- objectives. However, the majority of research in reinforcement learning (RL) and decision-theoretic planning assumes a single objective, or that multiple objectives can be handled via a predefined weighted sum over the objectives. Such approaches may oversimplify the underlying problem, and produce suboptimal results.
This extended abstract outlines the limitations of using a semi-blind iterative process to solve multi-objective decision making problems. Our extended paper serves as a guide for the application of explicitly multi-objective methods to difficult problems.
Originele taal-2English
TitelThe 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023)
UitgeverijInternational Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Pagina's1988-1990
Aantal pagina's3
Volume2023-May
ISBN van elektronische versie978-1-4503-9432-1
StatusPublished - mei 2023
EvenementThe 22nd International Conference on Autonomous Agents and Multiagent Systems - London, United Kingdom
Duur: 29 mei 20232 jun 2023
https://aamas2023.soton.ac.uk

Publicatie series

NaamProceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
ISSN van geprinte versie1548-8403

Conference

ConferenceThe 22nd International Conference on Autonomous Agents and Multiagent Systems
Verkorte titelAAMAS 2023
Land/RegioUnited Kingdom
StadLondon
Periode29/05/232/06/23
Internet adres

Bibliografische nota

Publisher Copyright:
© 2023 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.

Vingerafdruk

Duik in de onderzoeksthema's van 'A Brief Guide to Multi-Objective Reinforcement Learning and Planning: JAAMAS Track'. Samen vormen ze een unieke vingerafdruk.

Citeer dit