I am a Ph.D. student in the Department of Computer Science at Humboldt-Universität zu Berlin working with the Artificial Intelligence Group. My thesis advisors are Prof. Hans-Dieter Burkhard from Humboldt-Universität zu Berlin and Prof. Andrew Barto from University of Massachusetts Amherst.

Education

M.Sc. in Intelligent Systems from Instituto Tecnológico y de Estudios Superiores de Monterrey, Mexico 2002.
B.Sc. in Computer Systems from Instituto Tecnológico de Mérida, Mexico 1999.

Visiting Scholar collaborating with Prof. Andrew Barto at University of Massachusetts Amherst, USA, February-March 2006.
Visiting Scholar collaborating with Prof. Hans-Dieter Burkhard at Humboldt-Universität zu Berlin, Germany, September 2003.

Research Interest

My research concerns the design of intelligent computational systems capable to work autonomously in their environments, in order to accomplish goals safety and accurately. I am particularly interested in those computational systems, also called agents, that are able to improve their performances over time by means of supervised or reinforcement learning. At the present time, I am investigating architectures and algorithms for agents that benefit from the information provided by advisors in the form of behavior models, and from the experience generated by themselves through the interaction with their environments. My current research focuses mainly on the combination of function approximators and reinforcement learning algorithms based on temporal differences.

Fields of Research

- Artificial Intelligence
- Machine Learning
- Multiagent Systems

Publications

Victor Uc Cetina. Learning like Humans do: from Examples and Self-Generated Experiences. In Proceedings of the 6th International Conference on Human System Learning (ICHSL'08). Europia Productions, pages 101-108, ISBN 987-2-909285-46-4, Toulouse, France. 2008.

Victor Uc Cetina. Multilayer Perceptrons with Radial Basis Functions as Value Functions in Reinforcement Learning. In Proceedings of the 16th European Symposium on Artificial Neural Networks (ESANN'08). D-side Publications, pages 161-166, ISBN 2-930307-08-0, Bruges, Belgium. 2008.

Victor Uc Cetina. Autonomous Agent Learning using an Actor-Critic Algorithm and Behavior Models (Short Paper). In Proceedings of the 7th International Conference on Autonomous Agents and Multiagent Systems (AAMAS'08). IFAAMAS, pages 1353-1356, ISBN 978-0-9817381-0-9, Estoril, Portugal. 2008.

Victor Uc Cetina. Supervised Reinforcement Learning Using Behavior Models. In Proceedings of the 6th International Conference on Machine Learning and Applications (ICMLA'07). IEEE Computer Society Press, pages 336-341, ISBN 0-7695-3069-9, Cincinnati, Ohio, United States. 2007.

Victor Uc Cetina. A Multiagent Architecture for Concurrent Reinforcement Learning. In Proceedings of the 14th European Symposium on Artificial Neural Networks (ESANN'06). D-side Publications, pages 107-112, ISBN 2-930307-06-4, Bruges, Belgium. 2006.

Victor Uc Cetina. Tutorial de Protocolos de Ruteo para Redes Inalámbricas Móviles Ad-Hoc. Technical Report. Facultad de Matemáticas, Universidad Autónoma de Yucatán. Merida, Mexico. 2004.

Victor Uc Cetina. Optimizacion del Problema de Empacado de Material en 3-D mediante Algoritmos Geneticos. Master's thesis. Center for Intelligent Systems, Instituto Tecnológico y de Estudios Superiores de Monterrey. Monterrey, Mexico. 2002.

Victor Uc Cetina and Hugo Terashima. Container Loading Optimization Using a Genetic Algorithm. In Proceedings of the Workshop on Soft Computing at the 2nd Mexican International Conference on Artificial Intelligence (MICAI'02). Merida, Mexico. 2002.

Selected Talks

"Reinforcement Learning in Continuous State and Action Spaces". Deutsches Forschungszentrum für Kunstliche Intelligenz Labor Bremen, Germany. (25.06.2008)

"Learning Skills in the RoboCup Simulation League". Autonomous Learning Laboratory, University of Massachusetts Amherst, USA. (17.03.2006)

"Reinforcement Learning Algorithms". Facultad de Matematicas, Universidad Autonoma de Yucatan, Mexico. (19.12.2005)

"Learning where to Move and Kick the Ball on the Soccer Field". Institut für Informatik, Humboldt-Universität zu Berlin, Germany. (17.05.2005)