| Home | *Research* | Publications | Professional Activity | Course Work | Academic Background | Contact |
I believe that it is possible to represent "intelligent behaviour" as a computer program. Crucial to the sustenance of an intelligent agent situated in a realistic environment is its ability to learn and adapt to that environment. Reinforcement Learning provides a framework to model an agent that can improve its behaviour based on the experience it gathers by interacting with the environment.
The reinforcement learning problem is broad in its scope, encompassing a variety of realistic scenarios in a natural and elegant manner. Nevertheless, complex real-world problems often violate the assumptions that form the basis of traditional solutions to the reinforcement learning problem. Solutions to many problems of practical interest invariably demand the application of engineering approaches that exploit their underlying structure. Identifying techniques to solve complex reinforcement learning problems constitutes the broad scope of my research.
More details about my research are available from my publications.