BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning.
Lun WangZaynah JavedXian WuWenbo GuoXinyu XingDawn SongPublished in: IJCAI (2021)
Keyphrases
- reinforcement learning
- function approximation
- state space
- optimal policy
- countermeasures
- attack detection
- temporal difference
- markov decision processes
- machine learning
- autonomous learning
- temporal difference learning
- reinforcement learning algorithms
- model free
- learning process
- multi agent
- information systems
- neural network
- transfer learning
- np complete
- reinforcement learning methods
- transition model
- policy search
- power analysis
- robotic control