Can Reinforcement Learning Find Stackelberg-Nash Equilibria in General-Sum Markov Games with Myopically Rational Followers?
Han ZhongZhuoran YangZhaoran WangMichael I. JordanPublished in: J. Mach. Learn. Res. (2023)
Keyphrases
- nash equilibria
- markov games
- reinforcement learning
- nash equilibrium
- stochastic games
- multiagent reinforcement learning
- reinforcement learning algorithms
- incomplete information
- markov decision processes
- game theory
- special case
- game theoretic
- function approximation
- mixed strategy
- stackelberg game
- markov decision process
- control problems
- learning algorithm
- objective function
- pure strategy
- machine learning