Authors:
Richard Elderman
1
;
Leon J. J. Pater
1
;
Albert S. Thie
1
;
Madalina M. Drugan
2
and
Marco M. Wiering
1
Affiliations:
1
University of Groningen, Netherlands
;
2
Technical University of Eindhoven, Netherlands
Keyword(s):
Reinforcement Learning, Adversarial Setting, Markov Games, Cyber Security in Networks.
Related
Ontology
Subjects/Areas/Topics:
Agents
;
Artificial Intelligence
;
Artificial Intelligence and Decision Support Systems
;
Computational Intelligence
;
Distributed and Mobile Software Systems
;
Enterprise Information Systems
;
Evolutionary Computing
;
Knowledge Discovery and Information Retrieval
;
Knowledge Engineering and Ontology Development
;
Knowledge-Based Systems
;
Machine Learning
;
Multi-Agent Systems
;
Privacy, Safety and Security
;
Soft Computing
;
Software Engineering
;
Symbolic Systems
Abstract:
This paper focuses on cyber-security simulations in networks modeled as a Markov game with incomplete information and stochastic elements. The resulting game is an adversarial sequential decision making problem played with two agents, the attacker and defender. The two agents pit one reinforcement learning technique, like neural networks, Monte Carlo learning and Q-learning, against each other and examine their effectiveness against learning opponents. The results showed that Monte Carlo learning with the Softmax exploration strategy is most effective in performing the defender role and also for learning attacking strategies.