Blai Bonet

Computer Science Professor

Blai Bonet is a professor in the computer science department at Universidad Simón Bolívar, Venezuela. He received his Ph.D. degree in computer science ni 2004 from the University of California, Los Angeles. His research interests are in the areas of automated planning, heuristic search and knowledge representation. He has received several best paper awards or honorable mentions, including the 2009 and 2014 ICAPS Influential Paper Awards, and he is a co-author of the book titled "A Concise Introduction to Models and Methods for Automated Planning". Dr. Bonet has served as associate editor of Artificial Intelligence and the Journal of Artificial Intelligence, conference co-chair of ICAPS-12, program co-chair of AAAI-15, and has been a member of the Executive Council for ICAPS and AAAI.

Representation learning and synthesis for generalized planning

August 31 11:45 am - 1:00 pm (CEST)

Recent work in planning and learning is concerned with the task of inferring general plans from either models or data that solve multiple problems from the same domain (e.g., any blocks world problem). In this talk, I will address generalized planning from a model-based perspective conveying the progress made and challenges ahead. We will see how multiple problem instances can be captured with a finite but non-deterministic abstraction based on qualitative numerical planning (QNP) that can be solved using off-the-shelf (FOND) planners. QNP problems that involve numerical and boolean features can be used to capture multiple instances of a planning problem while avoiding undecidability issues.  The QNP abstraction can be either learned from samples and a first-order domain model, or directly learned from images (pixels) with the help of deep neural nets.