Universal Distributional Decision-based Black-box Adversarial Attack with Reinforcement Learning.
Yiran HuangYexu ZhouMichael HefenbrockTill RiedelLikun FangMichael BeiglPublished in: CoRR (2022)
Keyphrases
- black box
- reinforcement learning
- black boxes
- multi agent
- white box
- decision making
- function approximation
- optimal policy
- decision problems
- hybrid systems
- decision makers
- markov decision processes
- reinforcement learning algorithms
- model free
- decision rules
- co occurrence
- temporal difference
- state space
- dynamic programming
- test cases
- database
- optimal control
- countermeasures
- rule extraction
- learning algorithm
- data sets