10 papers
Transfer Learning in Bandits from Unknown Adaptive Policies: Problem-Dependent Lower and Upper Bounds
Adrien Prevost, Timothee Mathieu, Waris Radji +1
Transfer learning in stochastic multi-armed bandits is typically studied assuming that prior data forms a fixed offline dataset or is generated by a known source. In practice, hist…
Information-Based Exploration via Random Features for Reinforcement Learning
Waris Radji, Odalric-Ambrym Maillard
Representation learning has enabled classical exploration strategies to be extended to deep Reinforcement Learning (RL), but often makes algorithms more complex and theoretical gua…
Bandits for Efficient Experimentation: Adapting to Control Group, Preferences, and Context Drifts
Udvas Das, Waris Radji, Debabrota Basu +1
We consider a variant of the linear contextual stochastic multi-armed bandits, where the learner must provide recommendations to a group of users, each having its personalized pref…
Intrinsic-Energy Joint Embedding Predictive Architectures Induce Quasimetric Spaces
Anthony Kobanda, Waris Radji
Joint-Embedding Predictive Architectures (JEPAs) aim to learn representations by predicting target embeddings from context embeddings, inducing a scalar compatibility energy in a l…
How Hard is it to Confuse a World Model?
Waris Radji, Odalric-Ambrym Maillard
In reinforcement learning (RL) theory, the concept of most confusing instances is central to establishing regret lower bounds, that is, the minimal exploration needed to solve a pr…
The Confusing Instance Principle for Online Linear Quadratic Control
Waris Radji, Odalric-Ambrym Maillard
We revisit the problem of controlling linear systems with quadratic cost under unknown dynamics with model-based reinforcement learning. Traditional methods like Optimism in the Fa…
Octax: Accelerated CHIP-8 Arcade Environments for Reinforcement Learning in JAX
Waris Radji, Thomas Michel, Hector Piteau
Reinforcement learning (RL) research requires diverse, challenging environments that are both tractable and scalable. While modern video games may offer rich dynamics, they are com…
Offline Goal-Conditioned Reinforcement Learning with Projective Quasimetric Planning
Anthony Kobanda, Waris Radji, Mathieu Petitbois +2
Offline Goal-Conditioned Reinforcement Learning seeks to train agents to reach specified goals from previously collected trajectories. Scaling that promises to long-horizon tasks r…
Evaluating Interpretable Reinforcement Learning by Distilling Policies into Programs
Hector Kohler, Quentin Delfosse, Waris Radji +2
There exist applications of reinforcement learning like medicine where policies need to be ''interpretable'' by humans. User studies have shown that some policy classes might be mo…
Universal Adversarial Perturbations: Efficiency on a small image dataset
Waris Radji
Although neural networks perform very well on the image classification task, they are still vulnerable to adversarial perturbations that can fool a neural network without visibly c…