Hierarchical reinforcement learning using path clustering

In this paper we intend to study the possibility to improve the performance of the Q-Learning algorithm, by automatically finding subgoals and making better use of the acquired knowledge. This research explores a method that allows an agent to gather information about sequences of states that lead t...

Full description

Bibliographic Details
Main Author: Gil, Paulo (author)
Other Authors: Nunes, Luís (author)
Format: conferenceObject
Language:eng
Published: 2013
Subjects:
reinforcement learning
Q-Learning
subgoals
options
Online Access:http://hdl.handle.net/10071/5353
Country:Portugal
Oai:oai:repositorio.iscte-iul.pt:10071/5353

Internet

http://hdl.handle.net/10071/5353

Similar Items