Can Reinforcement Learning Find Stackelberg-Nash Equilibria in General-Sum Markov Games with Myopic Followers?
Han ZhongZhuoran YangZhaoran WangMichael I. JordanPublished in: CoRR (2021)
Keyphrases
- nash equilibria
- stochastic games
- multiagent reinforcement learning
- markov games
- reinforcement learning
- nash equilibrium
- incomplete information
- game theory
- reinforcement learning algorithms
- special case
- game theoretic
- markov decision processes
- mixed strategy
- stackelberg game
- pure strategy
- multiagent learning
- objective function
- infinite horizon
- decision problems
- dynamic programming
- computational complexity