The Allred Distinguished Lecture in Artificial Intelligence
Thomas G. Dietterich, Distinguished Professor in Computer Science and Director of Intelligent Systems Group at Oregon State University, will present “Managing Invasive Species and Wildfires by Solving Simulator-Defined Markov Decision Problems” at 10:10 a.m. on Wednesday, Nov. 4, in ETRL 101.
Abstract: Many ecosystem management problems can be formulated as Markov Decision Problems (MDPs). Unlike typical MDPs in robotics, the state and action spaces are often very large, because ecological phenomena take place over large landscapes. Another challenge of these problems is that the system dynamics are typically defined by computationally-expensive simulators.This talk will describe work motivated by two problems: managing tamarisk invasions in river networks and managing wildfire in ponderosa pine forests. For the tamarisk problem, I will describe algorithms that attempt to minimize the number of calls to the simulator needed to obtain a near-optimal management policy with high probability. For the wildfire problem, I will describe the policy gradient methods we are exploring and present MDPvis, a visualization tool to help programmers and end users understand the optimal policy and how the MDP behaves when it is controlled by that policy.
This is joint work with Claire Montgomery, Jo Albers, Ron Metoyer, Kim Hall, Rachel Houtman, Hailey Buckingham, Sean McGregor, Mark Crowley, and Majid Alkaee Taleghan.
Bio: Dr. Dietterich (AB Oberlin College 1977; MS University of Illinois 1979; PhD Stanford University 1984) is Distinguished Professor and Director of Intelligent Systems in the School of Electrical Engineering and Computer Science at Oregon State University, where he joined the faculty in 1985. In 1987, he was named a Presidential Young Investigator for the NSF. In 1990, he published, with Dr. Jude Shavlik, the book entitled Readings in Machine Learning, and he also served as the Technical Program Co-Chair of the National Conference on Artificial Intelligence (AAAI-90). From 1992-1998 he held the position of Executive Editor of the journal Machine Learning. The Association for the Advancement of Artifi- cial Intelligence named him a Fellow in 1994, the Association for Computing Machinery named him a Fellow in 2003, and the American Association for the Advancement of Science named him a Fellow in 2007. In 2000, he co-founded a free electronic journal: The Journal of Machine Learning Research, and he is currently a member of the Editorial Board. Since 2007, he has served as arXiv moderator for Machine Learning. He was Technical Program Chair of the Neural Information Processing Systems (NIPS) conference in 2000 and General Chair in 2001. He is Past-President of the International Machine Learning Society (IMLS), a member of the IMLS Board, and he also serves on the Advisory Board of the NIPS Foundation. He is President of the Association for the Advancement of Artificial Intelligence. Dr. Dietterich currently pursues interdisciplinary research at the boundary of computer science, ecology, and sustainability policy. He is part of the leadership team for OSU’s Ecosystem Informatics programs including the NSF Summer Institute in Ecoinformatics.
