Conference Proceeding Article
We propose a new, core task abstraction (CTA) approach to learning the relevant transition functions in model-based hierarchical reinforcement learning. CTA exploits contextual independences of the state variables conditional on the task-specific actions; its promising performance is demonstrated through a set of benchmark problems.
hierarchical reinforcement learning, core task abstraction
Computer Sciences | Databases and Information Systems
Intelligent Systems and Decision Analytics
AAMAS '16: Proceedings of the 2016 International Conference on Autonomous Agents and Multiagent Systems: May 9-13, 2016, Singapore
City or Country
Ann Arbor, MI
LI, Zhuoru; NARAYAN, Akshay; and Tze-Yun LEONG.
A core task abstraction approach to hierarchical reinforcement learning [Extended abstract]. (2016). AAMAS '16: Proceedings of the 2016 International Conference on Autonomous Agents and Multiagent Systems: May 9-13, 2016, Singapore. 1411-1412. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/3431
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.