Real-time Attacks Against Deep Reinforcement Learning Policies.
Buse G. A. TekgulShelly WangSamuel MarchalN. AsokanPublished in: CoRR (2021)
Keyphrases
- real time
- reinforcement learning
- optimal policy
- robotic control
- policy search
- markov decision process
- learning process
- control policies
- markov decision processes
- machine learning
- learning algorithm
- dynamic programming
- reinforcement learning algorithms
- control policy
- malicious attacks
- policy gradient methods
- decentralized control
- decision problems
- transfer learning
- vision system