Fiche de KAMIENNY Pierre-alexandre

Titre : Efficient adaptation of reinforcement learning agents: from model-free exploration to symbolic world models
Date : 4 octobre 2023
Heure: 09:00
Résumé : This thesis presents novel strategies within the framework of Meta-Reinforcement Learning, aiming to equip RL agents with the ability to adapt to out-of-domain tasks. The first part of the thesis focuses on model-free techniques to learn effective exploration strategies. We consider two scenarios: one where the agent is provided with a set of training tasks, enabling it to explicitly model the tasks and learn generalizable task representations; and another where the agent learns without rewards to maximize its state coverage. In the second part, we investigate into the application of symbolic regression, a powerful tool for developing predictive models that offer interpretability and exhibit enhanced robustness against distribution shifts. These models are subsequently integrated with model-based RL agents to improve their performance in out-of-domain tasks.
Lieu : Meta Paris