Shlomo Zilberstein

Shlomo Zilberstein (Hebrew: שלמה זילברשטיין; born 1960) 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] He graduated with a B.A. in Computer Science summa cum laude from Technion – Israel Institute of Technology in 1982, and a Ph.D. in Computer Science from University of California at Berkeley in 1993, advised by Stuart J. Russell.[2][3] He 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).

Shlomo Zilberstein
Born1960
Israel
Alma mater
Known forAnytime Algorithms
Decentralized Partially Observable Markov Decision Processes
Scientific career
Fields
  • Artificial Intelligence
  • Computer Science
InstitutionsUniversity of Massachusetts, Amherst
ThesisOperational Rationality Through Compilation of Anytime Algorithms (1993)
Doctoral advisorStuart J. Russell
Websitewww.cs.umass.edu/~shlomo/

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[5] at the University of Massachusetts, Amherst.[6] 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][9][10][11]

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.[12] Additionally, he served as chair of the conference committee for both the Twenty-Ninth and Thirtieth AAAI Conference on Artificial Intelligence.[13][14] The National Science Foundation awarded Dr. Zilberstein with the RIA, CAREER, and ITR awards.[15] In 2011, he was elected as a fellow of the Association for the Advancement of Artificial Intelligence.[16]

Selected publications
  • Bernstein, Daniel S.; Givan, Robert; Immerman, Niel; and Zilberstein, Shlomo (2002). "The Complexity of Decentralized Control of Markov Decision Processes" (PDF). Mathematics of Operations Research. 27 (4): 819–840. arXiv:1301.3836. doi:10.1287/moor.27.4.819.297.CS1 maint: multiple names: authors list (link)
  • Hansen, Eric A.; Zilberstein, Shlomo (2001). "LAO*: A Heuristic Search Algorithm that Finds Solutions with Loops" (PDF). Artificial Intelligence. 129 (1–2): 35–62. doi:10.1016/s0004-3702(01)00106-0.
  • Zilberstein, Shlomo (1996). "Using Anytime Algorithms in Intelligent Systems" (PDF). AI Magazine. 17 (3): 73–83.

References
  1. UMass Amherst CS faculty list
  2. Dr. Zilberstein's Ph.D. thesis
  3. His doctoral advisor and thesis as part of his academic genealogy
  4. Professional website description
  5. Resource-Bounded Reasoning Laboratory website
  6. UMass Amherst research groups
  7. Dr. Zilberstein's NSF Grant in 2002 in which the Dec-POMDP model was developed
  8. Dr. Zilberstein's NSF Grant in 2014 for Semi-Autonomous Systems (SAS) with direct applications to semi-autonomous driving
  9. Popular Mechanics news article on semi-autonomous systems
  10. NSF news article on semi-autonomous systems
  11. Phys.org news article on semi-autonomous systems
  12. JAIR editors and staff list from 2012
  13. AAAI 2015 conference committee
  14. AAAI 2016 conference committee
  15. List of NSF CAREER award recipients
  16. AAAI fellows list
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.