Open Access   Article Go Back

Optimally Facing the uncertainty : A brief survey on Reinforcement Learning

R. Raja Rajeswari1 , A. Pethalakshmi2

Section:Survey Paper, Product Type: Journal Paper
Volume-06 , Issue-04 , Page no. 45-48, May-2018

Online published on May 31, 2018

Copyright © R. Raja Rajeswari, A. Pethalakshmi . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

View this paper at   Google Scholar | DPI Digital Library

XML View
PDF Download

How to Cite this Paper

  • IEEE Citation
  • MLA Citation
  • APA Citation
  • BibTex Citation
  • RIS Citation

IEEE Style Citation: R. Raja Rajeswari, A. Pethalakshmi, “Optimally Facing the uncertainty : A brief survey on Reinforcement Learning,” International Journal of Computer Sciences and Engineering, Vol.06, Issue.04, pp.45-48, 2018.

MLA Style Citation: R. Raja Rajeswari, A. Pethalakshmi "Optimally Facing the uncertainty : A brief survey on Reinforcement Learning." International Journal of Computer Sciences and Engineering 06.04 (2018): 45-48.

APA Style Citation: R. Raja Rajeswari, A. Pethalakshmi, (2018). Optimally Facing the uncertainty : A brief survey on Reinforcement Learning. International Journal of Computer Sciences and Engineering, 06(04), 45-48.

BibTex Style Citation:
@article{Rajeswari_2018,
author = {R. Raja Rajeswari, A. Pethalakshmi},
title = {Optimally Facing the uncertainty : A brief survey on Reinforcement Learning},
journal = {International Journal of Computer Sciences and Engineering},
issue_date = {5 2018},
volume = {06},
Issue = {04},
month = {5},
year = {2018},
issn = {2347-2693},
pages = {45-48},
url = {https://www.ijcseonline.org/full_spl_paper_view.php?paper_id=356},
publisher = {IJCSE, Indore, INDIA},
}

RIS Style Citation:
TY - JOUR
UR - https://www.ijcseonline.org/full_spl_paper_view.php?paper_id=356
TI - Optimally Facing the uncertainty : A brief survey on Reinforcement Learning
T2 - International Journal of Computer Sciences and Engineering
AU - R. Raja Rajeswari, A. Pethalakshmi
PY - 2018
DA - 2018/05/31
PB - IJCSE, Indore, INDIA
SP - 45-48
IS - 04
VL - 06
SN - 2347-2693
ER -

           

Abstract

— Reinforcement Learning is a combination of supervised learning and unsupervised learning, the two main streams of Machine Learning .It has many applications in Artificial Intelligence arena. Multi Armed Bandits problem, a classical Reinforcement Learning task employs exploration and exploitation tradeoff. Efficient Bandit Algorithms for solving Bandit problem proides solutions for various problems from Dynamic pricing to online multi class prediction. This research article analyses the elements of Reinforcement learning, mathematical formulation of multi armed Bandits problem and attempts to present a naive RL algorithm for N-Queens problem for an instance of N=4 and concludes with applications of Reinforcement Learning .

Key-Words / Index Term

Reinforcement Learning, multiarmed Bandit problem, ϵ- Greedy algorithm

References

[1] Alpaydm, Introduction to Machine Learning, MIT Press, 2010.
[2] Dai Shi, Exploring Bandit algorithms for Automatic content selection, Barcelona, 2014.
[3] Ellis Horrowitz, Fundamentals of Computer Algorithms, Galgottia Publictions,1996
[4] Kakade et al, Efficient Bandit Algorithms for online multiclass prediction, Conference Proceedings, University of Pennysylvnia,2008.
[5] Nahum Shimkin, Reinforcement Learning –Basic algorithms, Learning in Complex Systems Lecture notes, Spring 2011.
[6] Prathamesh, Multi armed bandit approach for Dynamic pricing, M.Tech Dissertation, Iit, Mumbai, 2015
[7] Sutton and Barto, Reinforcement Learning – an introduction, The MIT Press, England, 2017.
[8] Szepesvari, Algorithms for Reinforcement Learning, Synthesis lectures on Artificial Intelligence and machine learning, 2009.
[9] http://cs.mcgill.ca/~dprecup/courses /AI/Lectures/ai-lecture13.pdf
[10] www.medium.com/machinelearning for humans .html