Artificial intelligence, cognitive science, machine learning, reinforcement learning, robot learning, sequential decision-making.
Professor Mahadevan's research interests span several subfields of artificial intelligence and computer science, including machine learning, multi-agent systems, planning, perception, and robotics. His research in machine learning has been eclectic, ranging from pioneering work in explanation-based learning where his thesis introduced the model of learning apprentices for knowledge acquisition from experts, to the first rigorous study of concept learning with prior determination knowledge using the framework of Probably Approximately Correct (PAC) learning. Over the past decade, his research has centered around a general framework for autonomous learning and sequential decision-making, which studies how agents embedded in real-world environments can acquire knowledge on how to act from a stream of noisy percepts. The framework is rigorously validated using temporal statistical process models, principally Markov decision processes. His recent research has focused on hierarchical probabilistic models, including hierarchical hidden Markov processes, semi-Markov decision processes, and hierarchical partially observable Markov decision processes. Professor Mahadevan has also developed state-of-the-art applications, including mobile robot navigation in indoor office environments, an active vision system for finding objects in cluttered rooms, and coordination among teams of factory agents optimizing production control.
Ph.D., Computer Science, Rutgers University (1990). Professor Mahadevan joined the College of Information and Computer Sciences at the University of Massachusetts, Amherst in Fall 2001. Previously, he was an Associate Professor at the Department of Computer Science and Engineering at Michigan State University from 1997-2001. From 1993-1997, he was an assistant professor in the Department of Computer Science and Engineering at the University of South Florida, Tampa. He worked at the IBM T.J. Watson Laboratories in Hawthorne, NY from 1990-1993. From 1986-89, he was a visiting scholar in the School of Computer Science at Carnegie Mellon University.
Professor Mahadevan is an Associate Editor of Machine Learning and the Journal of Machine Learning Research. From 1997-2000, he was on the editorial board of the Journal for AI Research. He has been on numerous program committees for AAAI, ICML, IJCAI, NIPS, and IROS conferences. In 2001 and 2000, he served as the area chair for reinforcement learning at the ICML and NIPS conferences. In 2001, he co-authored a paper with his students Rajbala Makar and Mohammad Ghavamzadeh that received the best student paper award in the 5th International Conference on Autonomous Agents. In 1999, he co-authored a paper with Gang Wang that received the best paper award (runner-up) at the 16th International Conference on Machine Learning. In 1993, he co-edited (with Jonathan Connell) the book Robot Learning published by Kluwer Academic Press. He is a co-founder of LookAhead Decisions Inc. based in Berkeley, CA. Professor Mahadevan received an NSF CAREER Award in 1995.