Function Approximation for Solving Stackelberg Equilibrium in Large Perfect Information Games.
Chun Kai LingJ. Zico KolterFei FangPublished in: AAAI (2023)
Keyphrases
- function approximation
- perfect information
- subgame perfect equilibrium
- game theory
- imperfect information
- nash equilibrium
- reinforcement learning
- nash equilibria
- card games
- stochastic games
- temporal difference
- game theoretic
- card game
- learning tasks
- mixed strategy
- radial basis function
- reinforcement learning algorithms
- game tree
- board game
- model free
- particle filter
- human players
- dynamic programming
- search algorithm
- optimal solution