Certified Adversarial Robustness for Deep Reinforcement Learning.
Björn LütjensMichael EverettJonathan P. HowPublished in: CoRL (2019)
Keyphrases
- reinforcement learning
- multi agent
- function approximation
- temporal difference
- reinforcement learning algorithms
- optimal control
- machine learning
- temporal difference learning
- model free
- markov decision processes
- computational efficiency
- real world
- state space
- mobile robot
- action selection
- artificial intelligence
- learning algorithm
- high robustness
- robotic control