Snooping Attacks on Deep Reinforcement Learning.
Matthew InkawhichYiran ChenHai Helen LiPublished in: AAMAS (2020)
Keyphrases
- reinforcement learning
- function approximation
- countermeasures
- reinforcement learning algorithms
- markov decision processes
- malicious attacks
- watermarking scheme
- machine learning
- traffic analysis
- security threats
- optimal policy
- model free
- action selection
- learning algorithm
- ddos attacks
- security mechanisms
- temporal difference
- state space
- action space
- reinforcement learning methods
- dynamic programming
- autonomous learning
- learning process
- learning classifier systems
- optimal control
- temporal difference learning
- malicious users