Title :
Hierarchical Reinforcement Learning with OMQ
Author :
Shen, Jing ; Liu, Haibo ; Gu, Guochang
Author_Institution :
Sch. of Comput. Sci. & Technol., Harbin Eng. Univ.
Abstract :
A novel method of hierarchical reinforcement learning, named OMQ, by integrating options into MAXQ is presented. In OMQ, the MAXQ is used as basic framework to design hierarchies experientially and learn online, and the option is used to construct hierarchies automatically. The performance of OMQ is demonstrated in taxi domain and compared with Option and MAXQ. The simulation results show that the OMQ is more practical than option and MAXQ in partial known environment
Keywords :
learning (artificial intelligence); OMQ; hierarchical reinforcement learning; Aggregates; Automata; Cognitive informatics; Computer science; Design engineering; Encoding; Formal specifications; Learning; Navigation; State-space methods; MAXQ; Option; hierarchical reinforcement learning;
Conference_Titel :
Cognitive Informatics, 2006. ICCI 2006. 5th IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
1-4244-0475-4
DOI :
10.1109/COGINF.2006.365550
