Nicolas Castanet — accepted AI-conference papers

2025

Imagine Beyond ! Distributionally Robust Autoencoding for State Space Coverage in Online Reinforcement Learning

Nicolas Castanet, Olivier Sigaud, Sylvain Lamprier

NeurIPS 2025poster

Goal-Conditioned Reinforcement Learning (GCRL) enables agents to autonomously acquire diverse behaviors, but faces major challenges in visual environments due to high-dimensional, semantically sparse observations. In the online setting, where agents learn representations while exploring, the latent…

Cited by 0 Source ↗Scholar ↗

2023

Stein Variational Goal Generation for adaptive Exploration in Multi-Goal Reinforcement Learning

Nicolas Castanet, Olivier Sigaud, sylvain lamprier

ICML 2023poster

In multi-goal Reinforcement Learning, an agent can share experience between related training tasks, resulting in better generalization for new tasks at test time. However, when the goal space has discontinuities and the reward is sparse, a majority of goals are difficult to reach. In this context, a…

Cited by 4 Source ↗PDF ↗Scholar ↗