Learning Parameterized Policies for Planning Annotated RL
- Harsha Kokel
- Junkyu Lee
- et al.
- 2023
- IJCAI 2023
Michael Katz is a principal research staff member at IBM T.J. Watson Research Center in Yorktown Heights, New York. His research interests are in the area of Artificial Intelligence (AI), focusing on automated planning and autonomous systems, as well as integration of planning and reinforcement learning techniques. He has won numerous awards, including ICAPS 2023 Influential paper award for his ICAPS 2008 paper Optimal Additive Composition of Abstraction-based Admissible Heuristics, co-authored with Carmel Domshlak, numerous gold/silver/bronze medals in both the first and the second CoRe Challenges (2022-2023) with the PARIS team, winner of the cost-optimal track of IPC2018 (Delfi) and runner-up of the satisficing track of IPC2014 (Mercury), as well as the winner of ICAPS 2011 Best Dissertation Award.
Michael is currently a member of ICAPS executive council (6 years term), having served as a program co-chair of ICAPS 2021. He is the Competition Liaison for ICAPS organization. Michael was a co-creator of the PRL workshop series and a co-organizer of several editions: PRL@ICAPS'20, PRL@ICAPS'22, PRL@IJCAI'22, PRL@ICAPS'23, and PRL@IJCAI'23. He was also a co-organizer of many HSDIP workshop editions: HSDIP'11,'13,'14,'15,'16,'18,'22. He was the Publicity Chair and Video Chair of ICAPS'15 and a lecturer at the ICAPS'13 Summer School. Michael regularly serves on the PC and SPCs of ICAPS, IJCAI and AAAI.
Michael Katz joined IBM T. J. Watson Research Center in 2017. Proir to that he was in IBM Watson Health and IBM Research Haifa, Israel.
Prior to joining IBM, Michael has spent two years in France and Germany, doing a postdoc hosted by Prof. 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, Germany.
Before that he was a 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.
Michael's PhD studies were done in the field of Artificial Intelligence. His PhD Thesis Implicit Abstraction Heuristics for Cost-Optimal Planning was the winner of the ICAPS Best Dissertation Award 2011.
Michael's tools for automated planning (also known as planners) has 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.