Information Acquisition Driven by Reinforcement in Non-Deterministic Environments

Naresh Babu Bynagari and Ruhul Amin
Additional contact information
Naresh Babu Bynagari: Director of Sales, Career Soft Solutions Inc, 145 Talmadge rd Edison NJ 08817, Middlesex, USA
Ruhul Amin: Senior Data Entry Control Operator (IT), ED-Maintenance Office, Bangladesh Bank (Head Office), Dhaka, BANGLADESH

American Journal of Trade and Policy, 2019, vol. 6, issue 3, 107-112

Abstract: What is the fastest way for an agent living in a non-deterministic Markov environment (NME) to learn about its statistical properties? The answer is to create "optimal" experiment sequences by carrying out action sequences that maximize expected knowledge gain. This idea is implemented by integrating information theory and reinforcement learning techniques. Experiments demonstrate that the resulting reinforcement-driven information acquisition (RDIA) method is substantially faster than standard random exploration for exploring particular NMEs. The investigation was studied apart from exploitation, and we evaluated the performance of different reinforcement-driven information acquisition variations to traditional random exploration.

Keywords: Non-deterministic Markov environment (NME); Reinforcement driven information acquisition (RDIA); Modeling agent-environment interaction; Q-learning (search for similar items in EconPapers)
JEL-codes: D83 (search for similar items in EconPapers)
Date: 2019
References: Add references at CitEc
Citations:

Downloads: (external link)
https://abc.us.org/ojs/index.php/ajtp/article/view/569/1071 Full text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ris:ajotap:0050

Access Statistics for this article

American Journal of Trade and Policy is currently edited by Charles A. Rarick

More articles in American Journal of Trade and Policy from Asian Business Consortium Asian Business Consortium, 10-B-6, Darussalam Tower, Mirpur Road, Dhaka-1216, Bangladesh.
Bibliographic data for series maintained by Alim Al Ayub Ahmed ( this e-mail address is bad, please contact ).