Shlomo Zilberstein

• Program

  AI Safety Science

• Institution

  University of Massachusetts Amherst

• Location

  USA

Dr. Shlomo Zilberstein’s research in artificial intelligence centers on automated reasoning and action, focusing on how uncertainty and limited computational resources impact autonomous agents. His work addresses the question of agent rationality when optimal decisions are infeasible, using probabilistic reasoning and decision theory to develop efficient planning algorithms and meta-level control techniques for decision-making.
Since joining UMass Amherst’s Manning College of Information and Computer Sciences in 1993, Zilberstein has served as professor and director of the Resource-Bounded Reasoning Lab. He previously led research at IDF and Shalev Computers in Israel and was a visiting professor at the Technion and the University of Caen.

In partnership with Dr. Bagdasarian, this project will develop a methodology that allows AI agents to evaluate the trustworthiness of other AI agents and adjust their own behavior accordingly.