6 papers
Learning Abstract World Models with a Group-Structured Latent Space
Thomas Delliaux, Nguyen-Khanh Vu, Vincent François-Lavet +2
Learning meaningful abstract models of Markov Decision Processes (MDPs) is crucial for improving generalization from limited data. In this work, we show how geometric priors can be…
Solving robust MDPs as a sequence of static RL problems
Adil Zouitine, Matthieu Geist, Emmanuel Rachelson
Designing control policies whose performance level is guaranteed to remain above a given threshold in a span of environments is a critical feature for the adoption of reinforcement…
The Overfocusing Bias of Convolutional Neural Networks: A Saliency-Guided Regularization Approach
David Bertoin, Eduardo Hugo Sanchez, Mehdi Zouitine +1
Despite transformers being considered as the new standard in computer vision, convolutional neural networks (CNNs) still outperform them in low-data regimes. Nonetheless, CNNs ofte…
RRLS : Robust Reinforcement Learning Suite
Adil Zouitine, David Bertoin, Pierre Clavier +2
Robust reinforcement learning is the problem of learning control policies that provide optimal worst-case performance against a span of adversarial environments. It is a crucial in…
Time-Constrained Robust MDPs
Adil Zouitine, David Bertoin, Pierre Clavier +2
Robust reinforcement learning is essential for deploying reinforcement learning algorithms in real-world scenarios where environmental uncertainty predominates. Traditional robust…
Bootstrapping Expectiles in Reinforcement Learning
Pierre Clavier, Emmanuel Rachelson, Erwan Le Pennec +1
Many classic Reinforcement Learning (RL) algorithms rely on a Bellman operator, which involves an expectation over the next states, leading to the concept of bootstrapping. To intr…