TY - GEN
T1 - Relational Abstractions for Generalized Reinforcement Learning on Symbolic Problems
AU - Karia, Rushang
AU - Srivastava, Siddharth
N1 - Funding Information:
We would like to thank the Research Computing Group at Arizona State University for providing compute hours for our experiments. This research was supported in part by the NSF under grant IIS 1942856.
Publisher Copyright:
© 2022 International Joint Conferences on Artificial Intelligence. All rights reserved.
PY - 2022
Y1 - 2022
N2 - Reinforcement learning in problems with symbolic state spaces is challenging due to the need for reasoning over long horizons. This paper presents a new approach that utilizes relational abstractions in conjunction with deep learning to learn a generalizable Q-function for such problems. The learned Q-function can be efficiently transferred to related problems that have different object names and object quantities, and thus, entirely different state spaces. We show that the learned, generalized Q-function can be utilized for zero-shot transfer to related problems without an explicit, hand-coded curriculum. Empirical evaluations on a range of problems show that our method facilitates efficient zero-shot transfer of learned knowledge to much larger problem instances containing many objects.
AB - Reinforcement learning in problems with symbolic state spaces is challenging due to the need for reasoning over long horizons. This paper presents a new approach that utilizes relational abstractions in conjunction with deep learning to learn a generalizable Q-function for such problems. The learned Q-function can be efficiently transferred to related problems that have different object names and object quantities, and thus, entirely different state spaces. We show that the learned, generalized Q-function can be utilized for zero-shot transfer to related problems without an explicit, hand-coded curriculum. Empirical evaluations on a range of problems show that our method facilitates efficient zero-shot transfer of learned knowledge to much larger problem instances containing many objects.
UR - http://www.scopus.com/inward/record.url?scp=85137914265&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85137914265&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85137914265
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 3135
EP - 3142
BT - Proceedings of the 31st International Joint Conference on Artificial Intelligence, IJCAI 2022
A2 - De Raedt, Luc
A2 - De Raedt, Luc
PB - International Joint Conferences on Artificial Intelligence
T2 - 31st International Joint Conference on Artificial Intelligence, IJCAI 2022
Y2 - 23 July 2022 through 29 July 2022
ER -