Enhanced Adversarial Strategically-Timed Attacks against Deep Reinforcement Learning.
Chao-Han Huck YangJun QiPin-Yu ChenYi OuyangI-Te Danny HungChin-Hui LeeXiaoli MaPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- multi agent
- countermeasures
- state space
- petri net
- function approximation
- machine learning
- reinforcement learning algorithms
- malicious attacks
- deep learning
- transfer learning
- markov decision processes
- multi agent reinforcement learning
- watermarking scheme
- learning algorithm
- model free
- security threats
- security protocols
- learning agent
- function approximators
- terrorist attacks
- neural network
- traffic analysis
- timed automata
- watermarking technique
- finite state machines
- optimal control
- supervised learning
- dynamic programming
- multi agent systems