Dr. Sridhar Mahadevan is an Associate Professor in the Department of Computer Science at the University of Massachusetts, Amherst. He received his PhD from Rutgers University in 1990. 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 PhD thesis introduced the learning apprentice model of knowledge acquisition from experts, as well as a rigorous study of concept learning with prior determination knowledge using the framework of Probably Approximately Correct (PAC) learning. In 1993, he co-edited (with Jonathan Connell) the book Robot Learning published by Kluwer Academic Press, one of the first books on the application of machine learning to robotics. Over the past decade, his research has centered around Markov decision processes and reinforcement learning, where his papers are among the most cited in the field. His recent work on spectral and wavelet methods for Markov decision processes has generated much attention, leading to a unified framework for learning representation and behavior. Professor Mahadevan is an Associate Editor for the Journal of Machine Learning Research. Previously, he served for many years as an Associate Editor for Journal of AI Research and the Machine Learning Journal. He has been on numerous program committees for AAAI, ICML, IJCAI, NIPS, ICRA, and IROS conferences, including area chair for at AAAI, 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. He was an invited tutorial speaker at ICML 2006, IJCAI 2007, and AAAI 2007.
