Publications

Journal Papers

Monte Carlo Tree Search Algorithms for Risk-Aware and Multi-Objective Reinforcement Learning. Conor F. Hayes, Mathieu Reymond, Diederik M. Roijers, Enda Howley and Patrick Mannion. Journal of Autonomous Agents and Multi-Agent Systems (JAAMAS). 2022. [pdf]

Expected Scalarised Returns Dominance: A New Solution Concept for Multi-Objective Decision Making. Conor F. Hayes, Timothy Verstraeten, Diederik M. Roijers, Enda Howley and Patrick Mannion. Neural Comput & Applic. https://doi.org/10.1007/s00521-022-07334-x. 2022. [pdf]

Scalar Reward is Not Enough : A response to Silver, Singh, Precup and Sutton. Peter Vamplew, Benjamin J. Smith, Johan Kallstrom, Gabriel Ramos, Roxana Radulescu, Diederik M. Roijers, Conor F. Hayes, Frederik Heintz, Patrick Mannion, Pieter J.K Libin, Richard Dazeley and Cameron Foale. Journal of Autonomous Agents and Multi-Agent Systems (JAAMAS). 2022. [pdf]

A Practical Guide to Multi-Objective Reinforcement Learning and Planning. Conor F. Hayes, Roxana Rădulescu, Eugenio Bargiacchi, Johan Källström, Matthew Macfarlane, Mathieu Reymond, Timothy Verstraeten, Luisa M. Zintgraf, Richard Dazeley, Fredrik Heintz, Enda Howley, Athirai A. Irissappane, Patrick Mannion, Ann Nowé, Gabriel Ramos, Marcello Restelli, Peter Vamplew and Diederik M. Roijers. Journal of Autonomous Agents and Multi-Agent Systems (JAAMAS). 2022. [pdf]

Conference Papers

Decision-Theoretic Planning for the Expected Scalarised Returns. Conor F. Hayes, Diederik M. Roijers, Enda Howley and Patrick Mannion. Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems (AAMAS). 2022. [pdf]

Distributional Monte Carlo Tree Search for Risk-Aware and Multi-Objective Reinforcement Learning. Conor F. Hayes, Mathieu Reymond, Diederik M. Roijers, Enda Howley and Patrick Mannion. Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS). 2021. [pdf] [poster] 

Workshop Papers

Multi-Objective Coordination Graphs for the Expected Scalarised Returns with Generative Flow Models. Conor F. Hayes, Timothy Verstraeten, Diederik M. Roijers, Enda Howley and Patrick Mannion. European Workshop on Reinforcement Learning. 2022. [pdf]

Multi-Objective Distributional Value Iteration. Conor F. Hayes, Diederik M. Roijers, Enda Howley and Patrick Mannion. The Adaptive Learning Agents Workshop 2022 at AAMAS. 2022. [pdf]

Actor-Critic Multi-Objective Reinforcement Learning for Non-Linear Utility Functions. Mathieu Reymond, Conor F. Hayes, Diederik M. Roijers, Denis Steckelmacher and Ann Nowé. The Multi-Objective Decision Making Workshop 2021. [pdf]

Risk-Aware and Multi-Objective Decision Making with Distributional Monte Carlo Tree Search. Conor F. Hayes, Mathieu Reymond, Diederik M. Roijers, Enda Howley and Patrick Mannion. The Adaptive Learning Agents Workshop 2021 at AAMAS. 2021. [pdf] 

Dominance Criteria and Solution Sets for the Expected Scalarised Returns. Conor F. Hayes, Timothy Verstraeten, Diederik M. Roijers, Enda Howley and Patrick Mannion. The Adaptive Learning Agents Workshop 2021 at AAMAS. 2021. [pdf]

Dynamic Thresholded Lexicographic Ordering.  Conor F. Hayes, Enda Howley and Patrick Mannion. The Adaptive Learning Agents Workshop 2020 at AAMAS. 2020. [pdf]

Preprints

Exploring the Pareto Front of Multi-Objective COVID-19 Mitigation Policies using Reinforcement Learning. Mathieu Reymond, Conor F. Hayes, Lander Willem, Roxana R ̆adulescu, Steven Abrams, Diederik M. Roijers, Enda Howley, Patrick Mannion, Niel Hens, Ann Nowé, Pieter Libin. ArXiv. 2022. [pdf]

PhD Thesis

Multi-Objective Reinforcement Learning and Planning for the Expected Scalarised Returns. Conor F. Hayes. PhD Thesis in Computer Science. University of Galway. 2022.

Master’s Thesis

Dynamic Economic Emissions Dispatch with Thresholded Lexicographic Ordering. Conor F. Hayes. Master’s Thesis in Computer Science. National University of Ireland Galway. 2019. [pdf]