Multi-Objective Decision Making Workshop at ECAI 2025
25 October 2025, Bologna, Italy
News
- 9 October 2025: The program is now online.
- 9 October 2025: We are happy to announce our second invited speaker for this year: Paolo Viappiani.
- 27 September 2025: We are happy to announce our first invited speaker for this year: Ivana Dusparic.
- 26 September 2025: The list of accepted papers is now online.
- 24 July 2025: Submissions are now closed. We received 19 submissions this year!
- 15 July 2025: The submission deadline has been extended to 23 July 2025!
- 25 February 2025: MODeM 2025 site launched
Multi-Objective Decision Making Workshop - 2025
In recent years there has been a growing awareness of the need for automated and assistive decision making systems to move beyond single-objective formulations when dealing with complex real-world issues, which invariably involve multiple competing objectives. The purpose of this workshop is to promote collaboration and cross-fertilisation of ideas between researchers working in different areas of multi-objective decision making in the context of intelligent systems, and to provide a forum for dissemination of high-quality multi-objective decision making research.
Previous editions of this workshop may be found at the following URLs:
The workshop targets high-quality original papers covering all aspects of multi-objective decision making, including, but not limited to, the list of topics below. The following is a non-exhaustive list of topics that we would like to cover in the workshop:
- Multi-objective/multi-criteria/multi-attribute decision making
- Multi-objective reinforcement learning
- Multi-objective planning and scheduling
- Multi-objective multi-agent decision making
- Multi-objective game theory
- Preference elicitation for MODeM
- Social choice and MODeM
- Multi-objective decision support systems
- Multi-objective metaheuristic optimisation (e.g. evolutionary algorithms) for autonomous agents and multi-agent systems
- Multi-objectivisation
- Ethical AI through multi-objective modelling
- Explainable AI through multi-objective modelling
- Interactive systems for MODeM
- Applications of MODeM
- Interdisciplinary work (MODeM research that relates to other fields)
- New benchmark problems for MODeM
Program Details
The workshop programme will consist of contributed original talks, invited talks, and a panel discussion. We might also ask participants to pre-record talks and make them available outside of the workshop sessions, on our Youtube channel.
Important Dates
Submission Details
Papers should be formatted according to the ECAI 2025 guidelines, and should be a maximum of 7 pages in length (with additional pages containing references only). Additionally, we welcome submission of preliminary results, i.e. work-in-progress, as well as visionary outlook papers that lay out directions for future research in a specific area, both up to 5 pages in length, although shorter papers are very much welcome, and will not be judged differently. Finally, we also accept summaries of recently published journal papers in the form of a 2-page abstract (we note that these type of submissions need not be anonymised).
All submissions will be peer-reviewed (double-blind). Accepted work will be allocated time for poster and/or oral presentation during the workshop.
Papers can be submitted through EasyChair.
Program
Saturday, 25 October
| 09:00 - 09:10 | Welcome & Opening Remarks |
| 09:10 - 10:30 | Session I (Chair: Pieter Libin) |
| 09:10 - 09:30 | Nic Wilson Two Families of Scale-Invariant Regret, and their Monotonicity Properties |
| 09:30 - 09:50 | Juan Camilo Rosero Lopez and Ivana Dusparic Explainable Multi-Objective Reinforcement Learning: challenges and considerations |
| 09:50 - 10:10 | Teresa Becerril Torres, Carlos Ignacio Hernández Castellanos and Roberto Santana Hermida Particle Swarm Algorithm for Multi-objective Reinforcement Learning |
| 10:10 - 10:30 | Vittoria Vineis, Giuseppe Perelli and Gabriele Tolomei A Participatory Learning Framework for Multi-Stakeholder Decision-Making |
| 10:30 - 11:00 | Coffee break |
| 11:00 - 12:30 | Session II (Chair: Nic Wilson) |
| 11:00 - 11:50 | Keynote talk Paolo Viappiani New Directions in Reasoning with Partial Preference Models and Elicitation |
| 11:50 - 12:10 | Gaurav Dixit and Kagan Tumer Preference-Conditioned Evolutionary Reinforcement Learning for Multi-Objective Continuous Control |
| 12:10 - 12:30 | Lingxiao Kong, Cong Yang, Oya Beyan and Zeyd Boukhers Multi-Objective Reinforcement Learning for Large Language Model Optimization: Visionary Perspective |
| 12:30 - 14:00 | Lunch break |
| 14:00 - 15:30 | Session III (Chair: Siddarth Iyer) |
| 14:00 - 14:15 | Guillaume Escamocher, Paolo Viappiani and Nic Wilson Computing Minimax Regret by Bounding the Weight Space From Within and Without |
| 14:15 - 14:30 | Simon Jaxy, Anton Theys, Patrick Willet, Christopher Carleton, Ralf Vandam and Pieter Libin Semi-Supervised Deep Learning for Archaeological Site Discovery: A multi-criteria evaluation study |
| 14:30 - 14:45 | Robert Susmaga, Izabela Szczech and Dariusz Brzezinski VISTA: VISualization of relation Topologies of Alternatives |
| 14:45 - 15:00 | Arnau Mayoral Macau, Manel Rodríguez-Soto, Daniele Meli, Martí Sánchez and Juan Antonio Rodriguez Aguilar Safety embedding: designing safe environments with lexicographic deep reinforcement learning |
| 15:00 - 15:15 | Vipul Patel, Anirudh Deodhar and Dagnachew Birru A Multi-Objective Genetic Algorithm for Healthcare Workforce Scheduling |
| 15:15 - 15:30 | Fares Chouaki, Aurélie Beynier, Nicolas Maudet and Paolo Viappiani Multi-Objective Categorical Deep Q-Networks |
| 15:30 - 16:00 | Coffee break |
| 16:00 - 17:40 | Session IV (Chair: Patrick Mannion) |
| 16:00 - 16:50 | Keynote talk Ivana Dusparic Multi-objective Reinforcement Learning for Self-adaptation in Large-scale Critical Infrastructures |
| 16:50 - 17:10 | Aabhash Dhakal and Tim Lachner Pareto-Informed Smart "Predict, then Optimize" for Multi-Objective Combinatorial Problems |
| 17:10 - 17:30 | Dariusz Grynia, Robert Susmaga, Izabela Szczech and Dariusz Brzezinski Lexicographic Improvement Strategy for TOPSIS |
| 17:30 - 17:40 | Closing remarks |
Accepted Papers
| Paper# | Details | Title | Authors |
|---|---|---|---|
| 1 | [Paper] | Two Families of Scale-Invariant Regret, and their Monotonicity Properties | Nic Wilson |
| 2 | [Paper] | Explainable Multi-Objective Reinforcement Learning: challenges and considerations | Juan Camilo Rosero Lopez and Ivana Dusparic |
| 3 | [Paper] | Computing Minimax Regret by Bounding the Weight Space From Within and Without | Guillaume Escamocher, Paolo Viappiani and Nic Wilson |
| 4 | [Paper] | Semi-Supervised Deep Learning for Archaeological Site Discovery: A multi-criteria evaluation study | Simon Jaxy, Anton Theys, Patrick Willet, Christopher Carleton, Ralf Vandam and Pieter Libin |
| 5 | [Paper] | VISTA: VISualization of relation Topologies of Alternatives | Robert Susmaga, Izabela Szczech and Dariusz Brzezinski |
| 8 | [Paper] | Particle Swarm Algorithm for Multi-objective Reinforcement Learning | Teresa Becerril Torres, Carlos Ignacio Hernández Castellanos and Roberto Santana Hermida |
| 9 | [Paper] | A Participatory Learning Framework for Multi-Stakeholder Decision-Making | Vittoria Vineis, Giuseppe Perelli and Gabriele Tolomei |
| 10 | [Paper] | Safety embedding: designing safe environments with lexicographic deep reinforcement learning | Arnau Mayoral Macau, Manel Rodríguez-Soto, Daniele Meli, Martí Sánchez and Juan Antonio Rodriguez Aguilar |
| 14 | [Paper] | Preference-Conditioned Evolutionary Reinforcement Learning for Multi-Objective Continuous Control | Gaurav Dixit and Kagan Tumer |
| 15 | [Paper] | Multi-Objective Reinforcement Learning for Large Language Model Optimization: Visionary Perspective | Lingxiao Kong, Cong Yang, Oya Beyan and Zeyd Boukhers |
| 16 | [Paper] | A Multi-Objective Genetic Algorithm for Healthcare Workforce Scheduling | Vipul Patel, Anirudh Deodhar and Dagnachew Birru |
| 17 | [Paper] | Multi-Objective Categorical Deep Q-Networks | Fares Chouaki, Aurélie Beynier, Nicolas Maudet and Paolo Viappiani |
| 18 | [Paper] | Pareto-Informed Smart "Predict, then Optimize" for Multi-Objective Combinatorial Problems | Aabhash Dhakal and Tim Lachner |
| 19 | [Paper] | Lexicographic Improvement Strategy for TOPSIS | Dariusz Grynia, Robert Susmaga, Izabela Szczech and Dariusz Brzezinski |
Invited Talks
Ivana Dusparic
Affiliation: Trinity College Dublin (Dublin, Ireland)Title: Multi-objective Reinforcement Learning for Self-adaptation in Large-scale Critical Infrastructures
Bio: Ivana Dusparic is a Professor in Computer Science and a Fellow of Trinity College Dublin, Ireland. Her research expertise is in the development of new reinforcement learning algorithms for self-adaptation in heterogenous systems, with particular focus on sustainability of large-scale infrastructures. She is currently a co-director of Research Ireland Centre for Research Training in AI and leads a number of projects on reinforcement learning and multi-agent systems in intelligent mobility and communication networks.
Paolo Viappiani
Affiliation:LAMSADE, CNRS and University Paris Dauphine (France)
Title: New Directions in Reasoning with Partial Preference Models and Elicitation
Bio: Paolo Viappiani is a CNRS researcher at LAMSADE, a computer science laboratory with a strong emphasis on decision theory. His research focuses on algorithmic decision theory, particularly on the elicitation and aggregation of preferences in various contexts, including multi-criteria decision-making, computational social choice, sequential decision-making, and recommender systems. He has published around fifty peer-reviewed papers in reputable venues and regularly serves on the program committees of major AI conferences, including IJCAI, ECAI, and UAI.
Program Committee
- Lucas Alegre, UFRGS
- Hendrik Baier, Eindhoven University of Technology
- William Bailey, Centre College
- Mattia Billa, Università di Modena e Reggio Emilia
- Alexandra Cimpean, Vrije Universiteit Brussel
- Gaurav Dixit, Oregon State University
- Brandon Fain, Duke University
- Veronica Guidetti, University of Modena and Reggio Emilia
- Conor F Hayes, Cognizant AI Lab
- Fredrik Heintz, Linköping University
- Thommen Karimpanal George, Deakin University
- Johan Källström, Linköping University
- Lawrence Mandow, Universidad de Málaga
- Dimitris Michailidis, University of Amsterdam
- Mathieu Reymond, Vrije Universiteit Brussel
- Manel Rodríguez-Soto, Spanish National Research Council (IIIA-CSIC)
- Fernando Santos, University of Amsterdam
- Francisco Javier Santos-Arteaga, Universidad Complutense de Madrid
- Atrisha Sarkar, University of Toronto
- Izabela Szczech, Poznan University of Technology
- Peter Vamplew, Federation University Australia
- Nic Wilson, University College Cork
Organization
This year's workshop is organised by:- Pieter Libin (Vrije Universiteit Brussel, BE)
- Patrick Mannion (University of Galway, IE)
- Roxana Rădulescu (Utrecht University, NL; Vrije Universiteit Brussel, BE)
- Willem Röpke (Vrije Universiteit Brussel, BE)
- Ali E. Abbas (University of Southern California, USA)
- Carlos A. Coello Coello (CINVESTAV-IPN, MX)
- Richard Dazeley (Deakin University, AU)
- Enda Howley (University of Galway, IE)
- Ann Nowé (Vrije Universiteit Brussel, BE)
- Patrice Perny (UPMC, FR)
- Marcello Restelli (Politecnico di Milano, IT)
- Diederik M. Roijers (Vrije Universiteit Brussel, BE; City of Amsterdam, NL)
- Peter Vamplew (Federation University Australia, AU)
- Nic Wilson (University College Cork, IE)
Contact
If you have any questions about the MODeM workshop, please contact the organizers at:
modem.organisers AT gmail.com