Automatic skill acquisition in reinforcement learning using graph centrality measures
Lists
Only you see this
Abstract
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.
BibTeX
@inproceedings{moradi2012automatic,
author = {Parham Moradi and Mohammad Ebrahim Shiri and Ali Ajdari Rad and Alireza Khadivi and Martin Hasler},
title = {{Automatic skill acquisition in reinforcement learning using graph centrality measures}},
booktitle = {Intell. Data Anal},
year = {2012},
url = {https://openreview.net/forum?id=gudg0jUeJu},
}Loading related content...