Certified Adversarial Robustness for Deep Reinforcement Learning.
Michael EverettBjörn LütjensJonathan P. HowPublished in: CoRR (2020)
Keyphrases
- learning agents
- reinforcement learning
- multi agent
- function approximation
- learning algorithm
- optimal control
- state space
- temporal difference
- optimal policy
- databases
- transfer learning
- digital images
- robotic control
- temporal difference learning
- model free
- markov chain
- supervised learning
- expert systems
- search algorithm
- website
- social networks
- artificial intelligence
- genetic algorithm