Back
  1. Home
  2. Profile of Francis Maes (ULiège)
Profil

Maes Francis

See author's contact details
Main Referenced Co-authors
Wehenkel, Louis  (9)
Ernst, Damien  (7)
Becker, Julien  (2)
Fonteneau, Raphaël  (2)
Castronovo, Michaël  (1)
Main Referenced Keywords
look-ahead tree search (2); reinforcement learning (2); Apprentissage structuré (1); automatic formula discovery (1); Bioinformatics (1);
Main Referenced Unit & Research Centers
GIGA-Bioinformatics (2)
Systèmes et Modélisation, GIGA-Research (1)
Main Referenced Disciplines
Computer science (11)

Publications (total 11)

The most downloaded
842 downloads
Perrick, P., Lupien St-Pierre, D., Maes, F., & Ernst, D. (2012). Comparison of Different Selection Strategies in Monte-Carlo Tree Search for the Game of Tron. In IEEE Conference on Computational and Intelligence in Games 2012 (pp. 242-249). https://hdl.handle.net/2268/132793

The most cited

16 citations (Scopus®)

Maes, F., Fonteneau, R., Wehenkel, L., & Ernst, D. (2012). Policy search in a space of simple closed-form formulas: towards interpretability of reinforcement learning. In Discovery Science 15th International Conference, DS 2012, Lyon, France, October 29-31, 2012. Proceedings (pp. 37-51). Berlin, Germany: Springer. doi:10.1007/978-3-642-33492-4_6 https://hdl.handle.net/2268/135635

Jung, T., Wehenkel, L., Ernst, D., & Maes, F. (March 2014). Optimized look-ahead tree policies: a bridge between look-ahead tree policies and direct policy search. International Journal of Adaptive Control and Signal Processing, 28 (3-5), 255-289. doi:10.1002/acs.2387
Peer Reviewed verified by ORBi

Maes, F., Fonteneau, R., Wehenkel, L., & Ernst, D. (2012). Policy search in a space of simple closed-form formulas: towards interpretability of reinforcement learning. In Discovery Science 15th International Conference, DS 2012, Lyon, France, October 29-31, 2012. Proceedings (pp. 37-51). Berlin, Germany: Springer. doi:10.1007/978-3-642-33492-4_6
Peer reviewed

Maes, F., Geurts, P., & Wehenkel, L. (2012). Embedding Monte Carlo search of features in tree-based ensemble methods. In P. Flach, T. De Bie, ... N. Cristianini (Eds.), Machine Learning and Knowledge Discovery in Data Bases (pp. 191-206). Springer.
Peer reviewed

Marcos Alvarez, A., Maes, F., & Wehenkel, L. (2012). Supervised learning to tune simulated annealing for in silico protein structure prediction. In M. Verleysen (Ed.), ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (pp. 49-54). Louvain-la-Neuve, Belgium: Ciaco.
Peer reviewed

Maes, F., Wehenkel, L., & Ernst, D. (2012). Learning to play K-armed bandit problems. In Proceedings of the 4th International Conference on Agents and Artificial Intelligence (ICAART 2012).
Peer reviewed

Perrick, P., Lupien St-Pierre, D., Maes, F., & Ernst, D. (2012). Comparison of Different Selection Strategies in Monte-Carlo Tree Search for the Game of Tron. In IEEE Conference on Computational and Intelligence in Games 2012 (pp. 242-249).
Peer reviewed

Castronovo, M., Maes, F., Fonteneau, R., & Ernst, D. (2012). Learning exploration/exploitation strategies for single trajectory reinforcement learning. In Proceedings of the 10th European Workshop on Reinforcement Learning (EWRL 2012) (pp. 1-9).
Peer reviewed

Maes, F., Becker, J., & Wehenkel, L. (2011). Prédiction structurée multitâche itérative de propriétés structurelles de protéines. In 7e Plateforme AFIA: Association Française pour l'Intelligence Artificielle (pp. 279). Editions Publibook.
Peer reviewed

Maes, F., Becker, J., & Wehenkel, L. (2011). Iterative multi-task sequence labeling for predicting structural properties of proteins. In ESANN 2011.
Peer reviewed

Maes, F., Wehenkel, L., & Ernst, D. (2011). Automatic discovery of ranking formulas for playing with multi-armed bandits. In Proceedings of the 9th European Workshop on Reinforcement Learning (EWRL 2011).
Peer reviewed

Maes, F., Wehenkel, L., & Ernst, D. (2011). Optimized look-ahead tree policies. In Proceedings of the 9th European Workshop on Reinforcement Learning (EWRL 2011).
Peer reviewed

Contact ORBi