Alexandre Rio

Alexandre Rio, Merwan Barlier, Igor Colin

Motivated by the increasing deployment of reinforcement learning in the real world, involving a large consumption of personal data, we introduce a differentially private (DP) policy gradient algorithm. We show that, in this setting, the introduction of Differential Privacy can be reduced to the computation of appropriate trust regions, thus avoiding the sacrifice of theoretical properties of the DP-less methods. Therefore, we show that it is possible to find the right trade-off between privacy noise and trust-region size to obtain a performant differentially private policy gradient algorithm. We then outline its performance empirically on various benchmarks. Our results and the complexity of the tasks addressed represent a significant improvement over existing DP algorithms in online RL.

Alexandre Rio, Marta Soare, Sihem Amer-Yahia

We address fairness in the context of sequential bundle recommendation, where users are served in turn with sets of relevant and compatible items. Motivated by real-world scenarios, we formalize producer-fairness, that seeks to achieve desired exposure of different item groups across users in a recommendation session. Our formulation combines naturally with building high quality bundles. Our problem is solved in real time as users arrive. We propose an exact solution that caters to small instances of our problem. We then examine two heuristics, quality-first and fairness-first, and an adaptive variant that determines on-the-fly the right balance between bundle fairness and quality. Our experiments on three real-world datasets underscore the strengths and limitations of each solution and demonstrate their efficacy in providing fair bundle recommendations without compromising bundle quality.

Alexandre Rio, Merwan Barlier, Igor Colin et al.

We address private deep offline reinforcement learning (RL), where the goal is to train a policy on standard control tasks that is differentially private (DP) with respect to individual trajectories in the dataset. To achieve this, we introduce PriMORL, a model-based RL algorithm with formal differential privacy guarantees. PriMORL first learns an ensemble of trajectory-level DP models of the environment from offline data. It then optimizes a policy on the penalized private model, without any further interaction with the system or access to the dataset. In addition to offering strong theoretical foundations, we demonstrate empirically that PriMORL enables the training of private RL agents on offline continuous control tasks with deep function approximations, whereas current methods are limited to simpler tabular and linear Markov Decision Processes (MDPs). We furthermore outline the trade-offs involved in achieving privacy in this setting.