Mathieu Reymond

Logo

Postdoctoral researcher at Mila.

About me

I am a postdoctoral researcher at Mila - the Quebec AI Institute working with Prof. Sarath Chandar. I completed my PhD at the Vrije Universiteit Brussel under the supervision of Prof. Ann Nowé and Diederik M. Roijers, where I focused on incorporating knowledge about the decision maker in multi-objective reinforcement learning. My current research focuses on reinforcement learning for scientific discovery through efficient exploration.


Publications

  1. Avalos, R., Reymond, M., Nowe, A., & Roijers, D. M. (2023). Local Advantage Networks for Multi-Agent Reinforcement Learning in Dec-POMDPs. Transactions on Machine Learning Research. https://openreview.net/forum?id=adpKzWQunW

  2. Reymond, M., Delgrange, F., Nowe, A., & Pérez, G. A. (2023). WAE-PCN: Wasserstein-autoencoded Pareto Conditioned Networks. In F. Cruz, C. F. Hayes , C. Wang, & C. Yates (Eds.), Proc. of the Adaptive and Learning Agents Workshop (ALA 2023): Vol. https://alaworkshop2023.github.io/ (15th ed., pp. 1–7). https://alaworkshop2023.github.io

  3. Reymond, M., Hayes, C. F., Steckelmacher, D., Roijers, D. M., & Nowe, A. (2023). Actor-critic multi-objective reinforcement learning for non-linear utility functions. Autonomous Agents and Multi-Agent Systems, 37(2). https://doi.org/10.1007/s10458-023-09604-x

  4. Reymond, M., Hayes, C. F., Willem, L., Radulescu, R., Abrams, S., Roijers, D. M., Howley, E., Mannion, P., Hens, N., Nowe, A., & Libin, P. (2022, September 19). Exploring the Pareto front of multi-objective COVID-19 mitigation policies using reinforcement learning. https://eccb2022.org/

  5. Avalos, R., Reymond, M., Nowe, A., & Roijers, D. M. (2022). Local Advantage Networks for Cooperative Multi-Agent Reinforcement Learning. International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2022, 1524–1526. https://aamas2022-conference.auckland.ac.nz

  6. Wang, S., Reymond, M., Irissappane, A. A., & Roijers, D. M. (2022). Near On-Policy Experience Sampling in Multi-Objective Reinforcement Learning. The 21st International Conference on Autonomous Agents and Multiagent Systems, 1756–1758. https://aamas2022-conference.auckland.ac.nz

  7. Reymond, M., Bargiacchi, E., & Nowe, A. (2022). Pareto Conditioned Networks. The 21st International Conference on Autonomous Agents and Multiagent Systems, 1110–1118. https://aamas2022-conference.auckland.ac.nz

  8. 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). https://doi.org/10.1007/s10458-022-09552-y

  9. Avalos, R., Reymond, M., Nowe, A., & Roijers, D. M. (2022). Local Advantage Networks for Multi-Agent Reinforcement Learning in Dec-POMDPs. Proc. of the Adaptive and Learning Agents Workshop (ALA 2023), https://ewrl.wordpress.com/past-ewrl/ewrl15-2022/, 1–17.

  10. Reymond, M., Hayes, C. F., Roijers, D. M., Steckelmacher, D., & Nowe, A. (2021, July 14). Actor-Critic Multi-Objective Reinforcement Learning for Non-Linear Utility Functions. http://modem2021.cs.nuigalway.ie/

  11. Hayes, C. F., Reymond, M., Roijers, D. M., Howley, E., & Mannion, P. (2021). Distributional Monte Carlo Tree Search for Risk-Aware and Multi-Objective Reinforcement Learning. The 20th International Conference on Autonomous Agents and Multiagent Systems, 1518–1520. https://aamas2021.soton.ac.uk/

  12. Roijers, D. M., Zintgraf, L. M., Libin, P., Reymond, M., Bargiacchi, E., & Nowe, A. (2021). Interactive Multi-Objective Reinforcement Learning in Multi-Armed Bandits with Gaussian Process Utility Models. In F. Hutter, K. Kersting, J. Lijffijt, & I. Valera (Eds.), ECML-PKDD 2020: Proceedings of the 2020 European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. Springer. https://doi.org/10.1007/978-3-030-67664-3_28

  13. Reymond, M., & Nowe, A. (2019, May 13). Pareto-DQN: Approximating the Pareto front in complex multi-objective decision problems. Proceedings of the Adaptive and Learning Agents Workshop 2019 (ALA-19) at AAMAS. https://ala2019.vub.ac.be

  14. Nevens, J., Radulescu, R., Reymond, M., Van Eecke, P., Efthymiadis, K., & Beuls, K. (2018). Hybrid AI for Visual Question Answering on CLEVR. In BNAIC 2018 Preproceedings (pp. 171–172). https://bnaic2018.nl

  15. Reymond, M., Patyn, C., Radulescu, R., Nowe, A., & Deconinck, G. (2018). Reinforcement Learning for Demand Response of Domestic Household Appliances. Proceedings of the Adaptive Learning Agents Workshop 2018 (ALA-18), 18–25. http://ala2018.it.nuigalway.ie/