Reinforcement Learning for Classical Planning: Viewing Heuristics as Dense Reward Generators
- ICAPS 2022
Shirin Sohrabi is a senior research scientist and research manager at IBM T.J. Watson Research Center in Yorktown Heights, New York. Her research interests are in the area of Artificial Intelligence (AI) with a focus on AI planning and its many applications. Shirin Sohrabi joined IBM T. J. Watson Research Center in 2012, after receiving her Ph.D. in Computer Science from University of Toronto. In 2020, she won the best system demonstration award at International Conference on Automated Planning and Scheduling (ICAPS) and in 2018, she received the runner up award for the best system demonstration at IJCAI for her work on Scenario Planning for Enterprise Risk Management. In 2016, she won the runner up award in the system demonstration competition for her work on Future State Projection as Planning. She has served as program co-chair of ICAPS 2020, as Novel Application Track co-chair of ICAPS 2018-2019, and as System Demonstration Track chair of AAAI 2018. She received the outstanding reviewer award at ICAPS 2016. She regularly serves on the Senior Program Committees of ICAPS, IJCAI, and AAAI. She is an ACM and AAAI senior member. She is a member of ICAPS executive council and also serves as the diversity and inclusion chair.
She was selected as an IBM Top Performer 2020 and invited to IBM Tech 2023.
1101 Kitchawan Rd Route 134 / P.O. Box 218
Yorktown Heights, NY 10598
See Visitor Information for directions to the lab.
GPS coordinates: -73.806002, 41.216056.