Automated AI For Decision Optimization with Reinforcement Learning
- Shankar Subramaniam
- Takayuki Osogami
- et al.
- AAAI 2023
My research interests are in the field of automated reasoning in Artificial Intelligence. I focus primarily on modeling and solving reasoning problems over graphical models. Graph based models, such as Bayesian and constraint networks, influence diagrams and Markov decision processes, have become a central paradigm for knowledge representation and reasoning in both Artificial Intelligence and computer science in general. These models use graphs (directed or undirected) that provide an intuitively appealing mechanism by which one can model highly interacting sets of variables. This allows for a concise representation of the knowledge that lends itself naturally to the design of efficient graph-based query processing algorithms. The guiding principle behind my approach to developing efficient algorithms for these models is to exploit the structural information that is revealed by the underlying graphical model.
I received a PhD in Computer Science from University of California, Irvine, USA.