Thèse Université de Sao Paulo - Université de Lorraine : "Safe reinforcement learning control for Markov jump linear systems"

The PhD will take place at Escola Politécnica of the University of São Paulo. The student will be co-supervised by Oswaldo L.V.Costa (USP) and Andre Marcorin de Oliveira (UNIFESP)  on the Brazilian side and J. Daafouz (CRAN, Nancy) and R. Postoyan (CRAN, Nancy) on the French side. A yearly mobility budget is secured, allowing the student to visit the French partners. 

For more details on the topic and the PhD in general, please see the enclosed PDF file.