Michael Katz

Research Staff Member

Categories

Automated Planning

Michael Katz is a research staff member at IBM T.J. Watson Research Center in Yorktown Heights. His research interests are in the area of AI focusing on automated planning and autonomous systems. Katz joined IBM T. J. Watson Research Center in 2017. Prior to that, he was in IBM Watson Health and IBM Research Haifa, Israel.

Before joining IBM, Katz spent two years in France and Germany, doing a postdoc hosted by Joerg Hoffmann at the Institut national de recherche en informatique et en automatique (INRIA), Nancy, France and in the Department of Computer Science, Saarland University. Katz also held postdoc at the Technion – Israel Institute of Technology, in the Faculty of Industrial Engineering & Management, where he also did his PhD, MSc, and BA studies. Katz’s PhD studies were done in the field of AI. His PhD “Implicit Abstraction Heuristics for Cost-Optimal Planning” won the ICAPS Best Dissertation Award 2011.

Katz’s tools for automated planning (also known as planners) have won numerous awards. Among them, Delfi, the winner of the cost-optimal track of the International Planning Competition (IPC) 2018 and Mercury, the runner-up of the satisficing track of the International Planning Competition (IPC) 2014.

Top Work

Reshaping Diverse Planning

Reshaping Diverse Planning

Automated Planning

Publications with the MIT-IBM Watson AI Lab

Reinforcement Learning for Classical Planning: Viewing Heuristics As Dense Reward Generators
Reinforcement Learning for Classical Planning: Viewing Heuristics As Dense Reward Generators
 
Reshaping Diverse Planning
Reshaping Diverse Planning
 
Online AI planning with graph neural networks and adaptive scheduling
Online AI planning with graph neural networks and adaptive scheduling
 
Top-Quality Planning: Finding Practically Useful Sets of Best Plans
Top-Quality Planning: Finding Practically Useful Sets of Best Plans