Automatic Skill Acquisition in Reinforcement Learning Using Graph Centrality Measures

Mechanisms on automatic discovery of macro actions or skills in reinforcement learning methods are mainly focused on subgoal discovery methods. Among the proposed algorithms, those based on graph centrality measures demonstrate a high performance gain. In this paper, we propose a new graph theoretic approach for automatically identifying and evaluating subgoals. Moreover, we propose a method for providing some useful prior knowledge for corresponding policy of developed skills based on two graph centrality measures, namely node connection graph stability and co-betweenness centrality. Investigating some benchmark problems, we show that the proposed approach improves the learning performance of the agent significantly.


Published in:
International Journal of Intelligent Data Analysis, 16, 1
Year:
2011
Keywords:
Laboratories:




 Record created 2011-02-09, last modified 2018-09-13


Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)