Shlomo Zilberstein (Hebrew: שלמה זילברשטיין; born 1960 in Tel Aviv, Israel) is an Israeli-American computer scientist. He is a Professor of Computer Science and Associate Dean for Research and Engagement in the College of Information and Computer Sciences at the University of Massachusetts, Amherst.[1,6] He graduated with a B.A. in Computer Science summa cum laude from Technion – Israel Institute of Technology in 1982, and received a Ph.D. in Computer Science from the University of California at Berkeley in 1993 with a thesis titled "Operational Rationality Through Compilation of Anytime Algorithms", advised by Stuart J. Russell.[2] Zilberstein is known for his contributions to artificial intelligence, anytime algorithms, multi-agent systems, and automated planning and scheduling algorithms, notably within the context of Markov decision processes (MDPs), Partially Observable MDPs (POMDPs), and Decentralized POMDPs (Dec-POMDPs).[12]
Research
His research is in the area of artificial intelligence, specifically automated planning, in addition to decision theory, reasoning under uncertainty, heuristic search, automated coordination and communication, and reinforcement learning.[4] He directs the Resource-Bounded Reasoning Laboratory at the University of Massachusetts, Amherst.[5] In 2002, Daniel S. Bernstein, Robert Givan, Neil Immerman, and Shlomo Zilberstein introduced the Decentralized POMDP which extends the widely used single-agent POMDP model to a multi-agent scenario (Dec-POMDP).[7] He has also developed AI algorithms for semi-autonomous systems with potential applications to semi-autonomous cars.[8]
Service and awards
He served as editor-in-chief of the Journal of Artificial Intelligence Research and associate editor of the Journal of Autonomous Agents and Multi-Agent Systems.[16] Additionally, he served as chair of the conference committee for both the Twenty-Ninth and Thirtieth AAAI Conference on Artificial Intelligence.[13]
The National Science Foundation awarded Dr. Zilberstein with the RIA, CAREER, and ITR awards.[15] He was elected as a fellow of the Association for the Advancement of Artificial Intelligence in 2011 and of the Association for Computing Machinery in 2021.[17]
Selected publications
In 1996, Shlomo Zilberstein published "Using Anytime Algorithms in Intelligent Systems" in AI Magazine and co-authored "Optimal Composition of Real-Time Systems" with Stuart J. Russell in Artificial Intelligence. In 2001, Eric A. Hansen published "LAO*: A Heuristic Search Algorithm that Finds Solutions with Loops" and "Monitoring and control of anytime algorithms: A dynamic programming approach" in Artificial Intelligence. In 2002, Daniel S. Bernstein, Robert Givan, Neil Immerman, and Shlomo Zilberstein published "The Complexity of Decentralized Control of Markov Decision Processes" in Mathematics of Operations Research. In 2004, Claudia V. Goldman and Shlomo Zilberstein published "Decentralized Control of Cooperative Systems: Categorization and Complexity Analysis" in the Journal of Artificial Intelligence Research, and Eric A. Hansen, Daniel S. Bernstein, and Shlomo Zilberstein published "Dynamic Programming for Partially Observable Stochastic Games" at AAAI. In Autonomous Agents and Multi-Agent Systems, Sven Seuken and Shlomo Zilberstein published "Formal Models and Algorithms for Decentralized Decision Making under Uncertainty" in 2008, followed by Christopher Amato, Daniel S. Bernstein, and Shlomo Zilberstein's "Optimizing Fixed-Size Stochastic Controllers for POMDPs and Decentralized POMDPs" in 2010. In 2012, Siddharth Srivastava, Neil Immerman, and Shlomo Zilberstein published "Applicability Conditions for Plans with Loops: Computability Results and Algorithms" in Artificial Intelligence.
External links
External links include Dr. Zilberstein's academic website and the Resource-Bounded Reasoning Laboratory website. Additionally, external resources include an overview, description, and publications within the field of the Decentralized Partially Observable Markov Decision Process (Dec-POMDP).
