Reinforcement Learning under Threats.
Víctor GallegoRoi NaveiroDavid Ríos InsuaPublished in: AAAI (2019)
Keyphrases
- reinforcement learning
- state space
- function approximation
- markov decision processes
- countermeasures
- optimal policy
- learning process
- model free
- multi agent
- dynamic programming
- information security
- machine learning
- temporal difference learning
- computer security
- reinforcement learning algorithms
- supervised learning
- malicious attacks
- security risks
- stochastic approximation
- optimal control
- robot control
- learning capabilities
- reward function
- learning algorithm