![](/images/graphics-bg.png)
An Empirical Investigation of Transfer Effects for Reinforcement Learning
Joint Authors
Jwo, Jung-Sing
Lin, Ching-Sheng
Lee, Cheng-Hsiung
Lo, Ya-Ching
Source
Computational Intelligence and Neuroscience
Issue
Vol. 2020, Issue 2020 (31 Dec. 2020), pp.1-10, 10 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2020-12-16
Country of Publication
Egypt
No. of Pages
10
Main Subjects
Abstract EN
Previous studies have shown that training a reinforcement model for the sorting problem takes very long time, even for small sets of data.
To study whether transfer learning could improve the training process of reinforcement learning, we employ Q-learning as the base of the reinforcement learning algorithm, apply the sorting problem as a case study, and assess the performance from two aspects, the time expense and the brain capacity.
We compare the total number of training steps between nontransfer and transfer methods to study the efficiencies and evaluate their differences in brain capacity (i.e., the percentage of the updated Q-values in the Q-table).
According to our experimental results, the difference in the total number of training steps will become smaller when the size of the numbers to be sorted increases.
Our results also show that the brain capacities of transfer and nontransfer reinforcement learning will be similar when they both reach a similar training level.
American Psychological Association (APA)
Jwo, Jung-Sing& Lin, Ching-Sheng& Lee, Cheng-Hsiung& Lo, Ya-Ching. 2020. An Empirical Investigation of Transfer Effects for Reinforcement Learning. Computational Intelligence and Neuroscience،Vol. 2020, no. 2020, pp.1-10.
https://search.emarefa.net/detail/BIM-1138930
Modern Language Association (MLA)
Jwo, Jung-Sing…[et al.]. An Empirical Investigation of Transfer Effects for Reinforcement Learning. Computational Intelligence and Neuroscience No. 2020 (2020), pp.1-10.
https://search.emarefa.net/detail/BIM-1138930
American Medical Association (AMA)
Jwo, Jung-Sing& Lin, Ching-Sheng& Lee, Cheng-Hsiung& Lo, Ya-Ching. An Empirical Investigation of Transfer Effects for Reinforcement Learning. Computational Intelligence and Neuroscience. 2020. Vol. 2020, no. 2020, pp.1-10.
https://search.emarefa.net/detail/BIM-1138930
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1138930