Mathieu Reymond
9 Papers
3 Citations
Mathieu Reymond is an academic researcher. The author has contributed to research in topics: Computer science & Reinforcement learning. The author has an hindex of 3, co-authored 7 publications.
Chat about Author
Papers
A practical guide to multi-objective reinforcement learning and planning
Conor Hayes,Roxana Radulescu,Eugenio Bargiacchi,John 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,Diederik M. Roijers +17 more
TL;DR: In this article , a guide to the application of multi-objective decision-making methods to difficult problems is presented, aimed at researchers who are already familiar with singleobjective reinforcement learning and planning methods and who wish to adopt a multiobjective perspective on their research.
Actor-critic multi-objective reinforcement learning for non-linear utility functions
TL;DR: A novel multi-objective reinforcement learning algorithm that successfully learns the optimal policy even for non-linear utility functions, avoiding the need to learn the full Pareto front.
16
Pareto Conditioned Networks
Mathieu Reymond,Eugenio Bargiacchi,Ann Now'e +2 more
- 11 Apr 2022
TL;DR: Pareto Conditioned Networks (PCN) is proposed, a method that uses a single neural network to encompass all non-dominated policies and is stable as it learns in a supervised fashion, thus avoiding moving target issues.
9
Monte Carlo tree search algorithms for risk-aware and multi-objective reinforcement learning
TL;DR: In this article , a Monte Carlo tree search algorithm is proposed to compute policies for nonlinear utility functions (NLU-MCTS) by optimising the utility of the different possible returns attainable from individual policy executions, resulting in good policies for both risk-aware and multiobjective settings.
Exploring the Pareto front of multi-objective COVID-19 mitigation policies using reinforcement learning
Mathieu Reymond,Conor Hayes,Lander Willem,Roxana Radulescu,Steven Abrams,Diederik M. Roijers,Enda Howley,Patrick Mannion,Niel Hens,Ann Now'e,Pieter Libin +10 more
TL;DR: This work contributes a multi-objective Markov decision process that encapsulates the stochastic compartment model that was used to inform policy makers during the COVID-19 epidemic and evaluates the solution returned by PCN, which correctly learns to reduce the social burden whenever the hospitalization rates are sufficiently low.
3