Optimal Attack and Defense for Reinforcement Learning.
Jeremy McMahanYoung WuXiaojin ZhuQiaomin XiePublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- optimal control
- intrusion detection
- function approximation
- dynamic programming
- state space
- multi agent systems
- ddos attacks
- reinforcement learning algorithms
- optimal design
- network security
- malicious users
- data sets
- approximate dynamic programming
- model free
- worst case
- mobile robot
- feature selection
- transfer learning
- supply chain
- hidden markov models
- recommender systems
- control policy
- multi agent