Reinforcement learning based a non-zero-sum game for secure transmission against smart jamming.
Chenyu ZhaoQing WangXiaofeng LiuChun LiLidong ShiPublished in: Digit. Signal Process. (2021)
Keyphrases
- reinforcement learning
- stochastic games
- game theory
- markov games
- reinforcement learning algorithms
- markov decision processes
- nash equilibria
- repeated games
- nash equilibrium
- games with incomplete information
- boolean games
- multiagent reinforcement learning
- game theoretic
- function approximation
- perfect information
- model free
- markov decision process
- multi agent
- state space
- incomplete information
- average reward
- data transmission
- temporal difference
- imperfect information
- video games
- learning algorithm
- game playing
- learning agent
- optimal strategy
- optimal policy
- reinforcement learning methods
- dynamic programming
- temporal difference learning
- pure strategy
- security issues
- policy iteration
- virtual world
- action selection
- security requirements
- game play
- serious games