Abdel Rodríguez

I am a Ph. D. student working at the COMO lab on a 2-year research project sponsored by the http://http://www.vlir.be/.

There are several examples of control systems handled by artificial intelligence techniques nowadays. One of these techniques is reinforcement learning. Reinforcement learning is originally defined in psychology as the way animals learn by trails and errors. It is a useful technique to control variables in dynamic systems where we can expect different reactions from the same actions. Several control systems should be modeled by continuous variables; however, reinforcement learning theory for continuous actions space is not as developed as for discrete decisions. The goal of this research is to study the theory of reinforcement learning for multi-agent systems in order to extend it to continuous actions space. Later on, dynamic systems defined by continuous variables will be tackled.

Journals and Lecture Notes

[2007, article | bibTeX]

I. G. R. G. M. M. Rodríguez Abdel; Bonet, "Judges System for Classifiers Specialization," International Journal of Biological, Biomedical and Medical Sciences, 2007.

Refereed Workshop

[{2008, inproceedings | bibTeX]

A. G. R. G. M. M. S. Y. N. A. Bonet Isis; Rodríguez, "Comparing Distance Measures with Visual Methods," in Proc. to appear in micai 2008, {2008.

• [2010] 22nd Benelux Conference on Artificial Intelligence (BNAIC 2010), Luxembourg, 25/10/2010 - 26/10/2010

• [2010] Cuba-Flanders Workshop on Machine Learning and Knowledge Discovery (CFWMLKD), Santa Clara, Cuba, 02/02/2010-05/02/2010
• [2008] 2nd International Workshop on Bioinformatics (IWOBI2008), Santa Clara, Cuba
• [2007] COMPUMAT 2007, Holgu\'in, Cuba
• [2007] Inform\'atica 2007, Havana, Cuba
• [2007] RECPAT 2007, Havana, Cuba
• [2006] UCIENCIA 2006, Havana, Cuba