2024 : 2 : 23
Parham Moradi

Parham Moradi

Academic rank: Associate Professor
ORCID:
Education: PhD.
ScopusId: 654
Faculty: Faculty of Engineering
Address: Department of Computer Engineering, Faculty of Engineering, University of Kurdistan
Phone:

Research

Title
Automatic skill acquisition in reinforcement learning using graph centrality measures
Type
JournalPaper
Keywords
Hierarchical reinforcement learning, skill cquisition, graph centrality measures, node connection graph stability,prior knowledge injection
Year
2011
Journal Intelligent Data Analysis
DOI
Researchers Martin Hasler ، Alireza Khadivi ، Ali Ajdarirad ، Mohammad Ebrahim Shiri ، Parham Moradi

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 sub-goals. 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.