Query-based targeted action-space adversarial policies on deep reinforcement learning agents.
Xian Yeow LeeYasaman EsfandiariKai Liang TanSoumik SarkarPublished in: ICCPS (2021)
Keyphrases
- training data
- reinforcement learning agents
- action space
- reinforcement learning
- state abstraction
- state space
- dynamic environments
- markov decision processes
- learning algorithm
- multi agent
- optimal policy
- reinforcement learning methods
- multi agent environments
- real valued
- transfer learning
- single agent
- machine learning
- action selection