Stealing Deep Reinforcement Learning Models for Fun and Profit.
Kangjie ChenTianwei ZhangXiaofei XieYang LiuPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- probabilistic model
- machine learning algorithms
- complex systems
- statistical models
- database
- generative model
- accurate models
- function approximation
- classification models
- markov decision processes
- process model
- least squares
- prior knowledge
- information systems
- information retrieval
- machine learning
- real time