Online optimal learning algorithm for Stackelberg games with partially unknown dynamics and constrained inputs.
Xiaohong CuiBinrui WangLina WangJiayu ChenPublished in: Neurocomputing (2021)
Keyphrases
- decision problems
- game theoretic
- optimal strategy
- learning algorithm
- nash equilibria
- game theory
- minority game
- nash equilibrium
- worst case
- dynamic programming
- online algorithms
- online game
- learning problems
- leader follower
- real time
- online learning
- dynamic model
- initially unknown
- stackelberg game
- active learning
- learning process
- reinforcement learning
- machine learning
- game playing
- educational games
- training samples
- supervised learning
- mixed strategy
- optimal solution