Certified Adversarial Robustness for Deep Reinforcement Learning.
Björn LütjensMichael EverettJonathan P. HowPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- multi agent
- function approximation
- markov decision processes
- state space
- multi agent reinforcement learning
- genetic algorithm
- optimal policy
- machine learning
- dynamic programming
- digital images
- video sequences
- information retrieval
- optimal control
- temporal difference
- reinforcement learning algorithms
- markov decision process
- learning agents
- neural network
- robotic control