Learning adversarial attack policies through multi-objective reinforcement learning.
Javier GarcíaRubén MajadasFernando FernándezPublished in: Eng. Appl. Artif. Intell. (2020)
Keyphrases
- reinforcement learning
- multi objective
- learning algorithm
- learning process
- evolutionary algorithm
- online learning
- optimal policy
- multi objective optimization
- learning problems
- learning tasks
- learning systems
- machine learning
- optimization algorithm
- state space
- multi agent
- autonomous learning
- optimization problems
- markov decision processes
- active learning
- countermeasures
- reinforcement learning algorithms
- learning agents
- temporal difference learning
- policy search
- reinforcement learning agents
- policy gradient methods