Multiple Domain Cyberspace Attack and Defense Game Based on Reward Randomization Reinforcement Learning.
Lei ZhangYu PanYi LiuQibin ZhengZhisong PanPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- domain specific
- multi agent
- learning process
- reinforcement learning algorithms
- reward function
- markov decision processes
- state space
- machine learning
- defense mechanisms
- eligibility traces
- secret key
- countermeasures
- function approximation
- network security
- transfer learning
- domain experts
- domain independent
- complex domains
- temporal abstractions
- intrusion detection
- deterministic domains
- total reward
- neural network