Portrait of Florence Clerc is unavailable

Florence Clerc

Alumni

Publications

Regularised RL improves sim-to-real transfer
Regularised reinforcement learning (RL) has provable robustness guarantees that should ease the transfer of policies from simulation to robo… (see more)ts, known as sim-to-real. Yet, weakly regularised algorithms like Proximal Policy Optimisation (PPO) remain the de facto choice in sim-to-real pipelines, while the practical benefits of regularisation for transfer remain poorly characterised. In this work, we study the sim-to-real performance of commonly used RL algorithms, with the aim of characterising the effects of regularisation on robotic performance. To that end, we derive Soft MellowMax Actor-Critic (SMM-AC), a novel regularised RL algorithm based on the soft mellowmax value function, which carries strong robustness guarantees. On MuJoCo continuous control benchmarks, SMM-AC is competitive with baselines like Soft Actor-Critic (SAC). On real robots, SMM-AC achieves higher return, while exhibiting greater robustness to perturbations in observations, the environment, and dynamics than baselines. Together, these results demonstrate that regularised RL improves real-world policy deployment through better robustness to the sim-to-real gap, and changing real-world conditions.
Behavioural pseudometrics for continuous-time diffusions
Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theory
Sokhna Diarra Mbacke
Pascal Germain
PAC-Bayesian Generalization Bounds for Adversarial Generative Models
Sokhna Diarra Mbacke
Pascal Germain
Sample Boosting Algorithm (SamBA) - An interpretable greedy ensemble classifier based on local expertise for fat data
Baptiste Bauvin
Cécile Capponi
Pascal Germain
Sokol Koço
J. Corbeil
Behavioural equivalences for continuous-time Markov processes
Towards a Classification of Behavioural Equivalences in Continuous-time Markov Processes