Title :
Automatic skill acquisition in Reinforcement Learning using connection graph stability centrality
Author :
Rad, Ali Ajdari ; Hasler, Martin ; Moradi, Parham
Author_Institution :
Sch. of Comput. & Commun. Sci., Ecole Polytech. Fed. de Lausanne, Lausanne, Switzerland
fDate :
May 30 2010-June 2 2010
Abstract :
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.
Keywords :
graph theory; learning (artificial intelligence); automatic skill acquisition; benchmark tasks; connection graph stability centrality; dynamic environment; high level behaviors; individual primitive actions; reinforcement learning; training agent behavior; trial-and-error interactions; two-room grid; Autonomous agents; Clustering algorithms; Computational modeling; Computer science; Learning; Partitioning algorithms; Performance evaluation; Space technology; Stability; State-space methods;
Conference_Titel :
Circuits and Systems (ISCAS), Proceedings of 2010 IEEE International Symposium on
Conference_Location :
Paris
Print_ISBN :
978-1-4244-5308-5
Electronic_ISBN :
978-1-4244-5309-2
DOI :
10.1109/ISCAS.2010.5537485