Review of Reinforcement Learning Techniques

  • Mohit MalpaniEmail author
  • Rejo Mathew
Conference paper
Part of the Lecture Notes on Data Engineering and Communications Technologies book series (LNDECT, volume 31)


The paper with the help of reinforcement learning techniques and its method helps to find the best techniques that can be used in cyber security to help defender protect the data against the attackers. The techniques have been used in a cyber security game and resulted in a game of an unfriendly consecutive decision making problem played between agents i.e. an attacker and a defender.


Cyber security game Network Agents Standard network Game procedure Reinforcement learning Neural Network 


  1. 1.
    Auer, P., Cesa-Bianchi, N., Fischer, P.: Finite-time analysis of the multi-armed bandit problem. Ma-chine Learn. 47, 235–256 (2002)CrossRefGoogle Scholar
  2. 2.
    Chung, K., Kamhoua, C., Kwiat, K., Kalbarczyk, Z., Iyer, K.: Game theory with learning for cyber security monitoring. IEEE HASE, pp. 1–8 (2016)Google Scholar
  3. 3.
    Neumann, J.V., Morgenstern, O.: Theory of games and economic behavior. Princeton University Press (2007)Google Scholar
  4. 4.
    Sutton, R.S., Barto, A.G.: Reinforcement learning: an introduction. The MIT press, Cambridge, MA (1998)zbMATHGoogle Scholar
  5. 5.
    Garivier, A., Moulines, E.: On upper-confidence bound policies for non-stationary bandit problems. ALT (2008)Google Scholar
  6. 6.
    Wang, Y., Li, T., Lin, C.: Backward q-learning: the combination of sarsa algorithm and q-learning. Eng. Appl. of AI 26, 2184–2193 (2013)CrossRefGoogle Scholar
  7. 7.
    Lin, L.-J.: Reinforcement learning for robots us-ing neural networks. PhD thesis, Carnegie Mellon University (1993)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Department IT, Mukesh Patel School of Technology Management and EngineeringNMIMS (Deemed-to-be University)MumbaiIndia

Personalised recommendations