136 citations
- Institut national de recherche en sciences et technologies du numériqueFR26 papers
- Laboratoire Lorrain de Recherche en Informatique et ses ApplicationsFR18 papers
- Centre National de la Recherche ScientifiqueFR6 papers
- Université de LorraineFR4 papers
- Université Toulouse III - Paul SabatierFR3 papers
- Centre Inria de l'université de BordeauxFR2 papers
- Centre Inria de SaclayFR2 papers
- École PolytechniqueFR2 papers
- Institut de Recherche en Informatique de ToulouseFR2 papers
- Institut Élie Cartan de LorraineFR2 papers
- Microsoft (United States)US2 papers
- University of LuxembourgLU2 papers
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2012★ 15 cited
On the Use of Non-Stationary Policies for Stationary Infinite-Horizon Markov Decision Processes
Bruno Scherrer, Boris Lesner
We consider infinite-horizon stationary -discounted Markov Decision Processes, for which it is known that there exists a stationary optimal policy. Using Value and Policy Iterat…
cs.LG2012★ 24 cited
A Dantzig Selector Approach to Temporal Difference Learning
Matthieu Geist, Bruno Scherrer, Alessandro Lazaric +1
LSTD is a popular algorithm for value function approximation. Whenever the number of features is larger than the number of samples, it must be paired with some form of regularizati…