Finding Needles in a Moving Haystack: Prioritizing Alerts with Adversarial Reinforcement Learning.
Liang TongAron LaszkaChao YanNing ZhangYevgeniy VorobeychikPublished in: AAAI (2020)
Keyphrases
- reinforcement learning
- function approximation
- multi agent
- learning algorithm
- optimal control
- state space
- robotic control
- stochastic approximation
- action selection
- model free
- learning problems
- decision support
- supervised learning
- database
- learning process
- moving objects
- case study
- knowledge base
- computer vision
- real time