Reward effect in reinforcement learning systems
Joint Authors
Bashir, Lubna Zaghlul
Walid, Zaynah
Source
Iraqi Journal of Computer, Communications and Control Engineering
Issue
Vol. 12, Issue 1 (30 Jun. 2012), pp.69-95, 27 p.
Publisher
Publication Date
2012-06-30
Country of Publication
Iraq
No. of Pages
27
Main Subjects
Abstract EN
Learning Classifier Systems (LCS), are a machine learning technique which combines reinforcement learning, evolutionary computing and other heuristics to produce adaptive systems.
The system HRC (Human –Rat- Cheese) focuses in creating artificial creature (Rat) using computer simulation, and learning it how to choose between two different basic behaviors, (approach / escape) combining them to perform complex behavior, which represents the final response in changing environment.
The HRC is built of two-classifier subsystems working together, each classifier system learns a simple behavior, and the system as a whole has as its learning goal the control of activities.
Flat architecture was used.
The flat organization allows distinguishing between two different learning activities : the learning of basic behavior and the learning of switch behavior.
One classifier system learns basic behavior, (approach / escape), i.e., it is used to learn the simulated robot single step movement in every direction in the environment.
Whereas the other classifier system learns to control the activities of basic classifier systems, i.e., it is used to learn to choose between basic behaviors using suppression as a composition mechanism to chose between two basic behaviors which represent complex behavior.
Simple experiments were executed for HRC : comparing and contrasting the effect of the reinforcement learning using reward & punishment with learning using reward only.
Experiment results show that the run using reinforcement learning with reward only is unable to perform as well as the run with reinforcement learning with reward and punishment.
American Psychological Association (APA)
Bashir, Lubna Zaghlul& Walid, Zaynah. 2012. Reward effect in reinforcement learning systems. Iraqi Journal of Computer, Communications and Control Engineering،Vol. 12, no. 1, pp.69-95.
https://search.emarefa.net/detail/BIM-320370
Modern Language Association (MLA)
Bashir, Lubna Zaghlul& Walid, Zaynah. Reward effect in reinforcement learning systems. Iraqi Journal of Computer, Communications and Control Engineering Vol. 12, no. 1 (2012), pp.69-95.
https://search.emarefa.net/detail/BIM-320370
American Medical Association (AMA)
Bashir, Lubna Zaghlul& Walid, Zaynah. Reward effect in reinforcement learning systems. Iraqi Journal of Computer, Communications and Control Engineering. 2012. Vol. 12, no. 1, pp.69-95.
https://search.emarefa.net/detail/BIM-320370
Data Type
Journal Articles
Language
English
Notes
Includes appendices : p. 80-95
Record ID
BIM-320370