Matteo Gagliolo
Postdoc researcher, CoMo, Vrije Universiteit Brussel (VUB)Brussels, Belgium
Research field: Computer and Information Science - Artificial Intelligence
Single/multi-agent reinforcement learning, bandit problems, online learning.
Social learning, evolutionary game theory.
Recurrent neural networks. Evolutionary computation.
Algorithm portfolios. Survival analysis.
Publications
-
Book Section (1)
-
Matteo Gagliolo, Catherine Legrand (2010) Algorithm Survival Analysis, 161-184.
-
-
Conference Proceedings (10)
-
Matteo Gagliolo, Jürgen Schmidhuber (2010) Algorithm Selection as a Bandit Problem with Unbounded Losses, 82-96. In Learning and Intelligent Optimization - LION4.
-
Matteo Gagliolo, Catherine Legrand, Mauro Birattari (2009) Mixed-Effects Modeling of Optimisation Algorithm Performance., 150-154. In Engineering Stochastic Local Search Algorithms. SLS 2009.
-
Matteo Gagliolo, Jürgen Schmidhuber (2008) Towards Distributed Algorithm Portfolios, 634-643. In International Symposium on Distributed Computing and Artificial Intelligence 2008 (DCAI 2008).
-
Matteo Gagliolo, Jürgen Schmidhuber (2007) Learning restart strategies, 792-797. In IJCAI 2007 - Twentieth International Joint Conference on Artificial Intelligence, vol. 1.
-
Matteo Gagliolo, Jürgen Schmidhuber (2006) Dynamic Algorithm Portfolios.
-
Jürgen Schmidhuber, Matteo Gagliolo, Daan Wierstra et al. (2006) Evolino for Recurrent Support Vector Machines, 593-598.
-
Matteo Gagliolo, Jürgen Schmidhuber (2006) Impact of censored sampling on the performance of restart strategies, 167-181. In Principle and Practice of Constraint Programming - CP 2006, 12th International Conference, CP 2006, Nantes, France, September 25-29, 2006, Proceedings.
-
Matteo Gagliolo, Jürgen Schmidhuber (2005) A Neural Network Model for Inter-Problem Adaptive Online Time Allocation, 7-12. In Artificial Neural Networks: Formal Models and Their Applications - ICANN 2005, 15th International Conference, Warsaw, Poland, September 11-15, 2005, Proceedings, Part 2.
-
Jürgen Schmidhuber, Viktor Zhumatiy, Matteo Gagliolo (2004) Bias-Optimal Incremental Learning of Control Sequences for Virtual Robots, 658-665.
-
Davide Anguita, Matteo Gagliolo (2002) {MDL} Based Model Selection for Relevance Vector Regression, 468-473. In Artificial Neural Networks - ICANN 2002.
-
-
Journal Article (4)
-
Matteo Gagliolo, Jürgen Schmidhuber (2011) Algorithm portfolio selection as a bandit problem with unbounded losses, 49-86. In Annals of Mathematics and Artificial Intelligence 61 (2).
-
Jürgen Schmidhuber, Daan Wierstra, Matteo Gagliolo et al. (2007) Training recurrent networks by Evolino, 757-779. In Neural computation 19 (3).
-
Matteo Gagliolo (2007) Universal Search. In Scholarpedia 2 (11).
-
Matteo Gagliolo, Jürgen Schmidhuber (2006) Learning dynamic algorithm portfolios, 295-328. In Annals of Mathematics and Artificial Intelligence 47 (3-4).
-
-
Report (1)
-
Matteo Gagliolo, Jürgen Schmidhuber (2008) Algorithm Selection as a Bandit Problem with Unbounded Losses..
-
-
Working Paper (3)
-
Matteo Gagliolo (2006) Dynamic Meta Learning.
-
Matteo Gagliolo, Jürgen Schmidhuber (2006) Gambling in a Computationally Expensive Casino: Algorithm Selection as a Bandit Problem.
-
Matteo Gagliolo, Jürgen Schmidhuber (2005) Towards Life-Long Meta Learning.
-
Biographical Information
No biographical information added yet.
CV
Professional Experience
2010 - Present
Jun 2008 - May 2009
Sep 2002 - Mar 2010
Doctoral researcher at IDSIA
Lugano, Switzerland
Classes taught:
Intelligent Systems (USI)
Algoritmi e numerica (SUPSI)
Programmazione e linguaggi (SUPSI)
Lugano, Switzerland
Classes taught:
Intelligent Systems (USI)
Algoritmi e numerica (SUPSI)
Programmazione e linguaggi (SUPSI)
Education
Contact Information
| Webpage: | http://como.vub.ac.be/~mgagliol/ |
Publication Statistics
Graphed by cumulative total
Graphed by month
Graphed by day
Graphed by day
Data temporarily unavailable.
Not enough data available.
Public Groups
Public groups Matteo is a member of
- Not a member of any groups yet.
- Find new public groups.
Public groups Matteo is following
Destinations
Sign up today - FREE
Mendeley saves you time finding and organizing research. Learn more