Constructing Temporally Extended Actions through Incremental Community Detection
Joint Authors
Source
Computational Intelligence and Neuroscience
Issue
Vol. 2018, Issue 2018 (31 Dec. 2018), pp.1-13, 13 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2018-04-23
Country of Publication
Egypt
No. of Pages
13
Main Subjects
Abstract EN
Hierarchical reinforcement learning works on temporally extended actions or skills to facilitate learning.
How to automatically form such abstraction is challenging, and many efforts tackle this issue in the options framework.
While various approaches exist to construct options from different perspectives, few of them concentrate on options’ adaptability during learning.
This paper presents an algorithm to create options and enhance their quality online.
Both aspects operate on detected communities of the learning environment’s state transition graph.
We first construct options from initial samples as the basis of online learning.
Then a rule-based community revision algorithm is proposed to update graph partitions, based on which existing options can be continuously tuned.
Experimental results in two problems indicate that options from initial samples may perform poorly in more complex environments, and our presented strategy can effectively improve options and get better results compared with flat reinforcement learning.
American Psychological Association (APA)
Xu, Xiao& Yang, Mei& Li, Ge. 2018. Constructing Temporally Extended Actions through Incremental Community Detection. Computational Intelligence and Neuroscience،Vol. 2018, no. 2018, pp.1-13.
https://search.emarefa.net/detail/BIM-1130630
Modern Language Association (MLA)
Xu, Xiao…[et al.]. Constructing Temporally Extended Actions through Incremental Community Detection. Computational Intelligence and Neuroscience No. 2018 (2018), pp.1-13.
https://search.emarefa.net/detail/BIM-1130630
American Medical Association (AMA)
Xu, Xiao& Yang, Mei& Li, Ge. Constructing Temporally Extended Actions through Incremental Community Detection. Computational Intelligence and Neuroscience. 2018. Vol. 2018, no. 2018, pp.1-13.
https://search.emarefa.net/detail/BIM-1130630
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1130630