Optimally Deceiving a Learning Leader in Stackelberg Games.
Georgios BirmpasJiarui GanAlexandros HollenderFrancisco J. Marmolejo CossíoNinad RajgopalAlexandros A. VoudourisPublished in: NeurIPS (2020)
Keyphrases
- learning process
- unsupervised learning
- leader follower
- game theory
- learning algorithm
- active learning
- stackelberg game
- knowledge acquisition
- supervised learning
- learning agents
- digital games
- foreign language learners
- neural network
- inductive inference
- learning community
- learning experience
- worst case
- reinforcement learning