Automatic skill acquisition in Reinforcement Learning using connection graph stability centrality

Reinforcement Learning (RL) is an approach for training agent's behavior through trial-and-error interactions with a dynamic environment. An important problem of RL is that in large domains an enormous number of decisions are to be made. Hence, instead of learning using individual primitive actions, an agent could learn much faster if it could form high level behaviors known as skills. Graph-based approach, that maps the RL problem to a graph, is one of the several approaches proposed to identify the skills to learn automatically. In this paper we propose a new centrality measure for identifying bottleneck nodes crucial to develop useful skills. We will show through simulations for two benchmark tasks, namely, two-room grid and taxi driver that a procedure based on the proposed measure performs better than the procedure based on closeness and node betweenness centrality.


Published in:
Proceedings of 2010 IEEE International Symposium on Circuits and Systems (ISCAS), 697 - 700
Presented at:
ISCAS 2010, Paris, France, May 30 2010-June 2 2010
Year:
2010
Publisher:
Ieee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa
ISBN:
978-1-4244-5308-5
Keywords:
Laboratories:




 Record created 2010-09-13, last modified 2018-03-17

External link:
Download fulltext
URL
Rate this document:

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