The European Workshop on Reinforcement Learning is the gathering hub of the RL research community in Europe and one of the main world-class events in RL. UPF contributed with six papers in its 17th edition in Toulouse:

• Bisimulation Metrics are Optimal Transport Distances, and Can be Computed Efficiently. Sergio Calo Oliveira, Anders Jonsson, Gergely Neu, Ludovic Schwartz, Javier Segovia-Aguas (also accepted at NeurIPS 2024)

• Adversarial Contextual Bandits Go Kernelized. Gergely Neu, Julia Olkhovskaya, Sattar Vakili (also accepted at ALT 2024)

• Using a Learned Policy Basis to Optimally Solve Reward Machines. Guillermo Infante, David Kuric, Vicenç Gómez, Anders Jonsson, Herke van Hoof (also accepted at ICAPS 2024)

• Offline RL via Feature-Occupancy Gradient Ascent. Gergely Neu, Nneka Okolo

• Distributed Constrained Multi-Agent Reinforcement Learning with Consensus and Networked Communication. Santiago Amaya-Corredor, Miguel Calvo-Fullana, Anders Jonsson

• Enhancing Exploration via Off-Reward Dynamic Reference Reinforcement Learning. Yamen Habib, Dmytro Grytskyy, Rubén Moreno-Bote