Adapting attackers and defenders patrolling strategies: A reinforcement learning approach for Stackelberg security games.
Kristal K. TrejoJulio B. ClempnerAlexander S. PoznyakPublished in: J. Comput. Syst. Sci. (2018)
Keyphrases
- reinforcement learning
- multi agent
- leader follower
- mixed strategy
- markov decision processes
- state space
- learning agents
- machine learning
- cooperative
- function approximation
- learning algorithm
- model free
- multi agent systems
- game theory
- multi agent reinforcement learning
- robotic control
- realistic settings
- resource constrained
- temporal difference
- action selection
- multi robot
- optimal control
- transfer learning
- learning process