Calendrier

Séminaire : Regularization and Robustness in Reinforcement Learning

Séminaire : Regularization and Robustness in Reinforcement Learning
Séminaire du GERAD conjoint avec la Chaire de recherche du Canada sur la prise de décision en incertitude

Regularization and Robustness in Reinforcement Learning

23 octobre 2023   11 h — 12 h

Esther Derman MILA, Canada

Séminaire en format hybride au local 4488 du GERAD ou Zoom.

Robust Markov decision processes (MDPs) aim to handle changing or partially known system dynamics. To solve them, one typically resorts to robust optimization methods. However, this significantly increases computational complexity and limits scalability in both learning and planning. On the other hand, regularized MDPs show more stability in policy learning without impairing time complexity. Yet, they generally do not encompass uncertainty in the model dynamics. In this talk, I will show how we can learn robust MDPs using proper regularization, so as to reduce planning and learning in robust MDPs to regularized MDPs.

Date

Lundi 23 octobre 2023
Débute à 11h00

Prix

gratuit

Contact

Lieu

Séminaire hybride au GERAD
Zoom et salle 4488
Pavillon André-Aisenstadt
Campus de l'Université de Montréal
2920, chemin de la Tour
Montréal Québec H3T 1J4
Canada
AA-4488

Catégories