Deceptive Reinforcement Learning Under Adversarial Manipulations on Cost Signals.
Yunhan HuangQuanyan ZhuPublished in: GameSec (2019)
Keyphrases
- reinforcement learning
- multi agent
- signal processing
- reinforcement learning algorithms
- total cost
- state space
- independent component analysis
- machine learning
- high cost
- model free
- cost sensitive
- markov decision processes
- dynamic programming
- learning algorithm
- supply chain
- optimal control
- np hard
- genetic algorithm
- data mining
- expected cost
- markov decision process
- reinforcement learning methods
- robotic control