Inducing Stackelberg Equilibrium through Spatio-Temporal Sequential Decision-Making in Multi-Agent Reinforcement Learning.
Bin ZhangLijuan LiZhiwei XuDapeng LiGuoliang FanPublished in: CoRR (2023)
Keyphrases
- multi agent reinforcement learning
- sequential decision making
- reinforcement learning
- game theory
- nash equilibria
- stochastic games
- nash equilibrium
- mixed strategy
- single commodity
- multi agent learning
- decision problems
- evolutionary game theory
- game theoretic
- multi agent systems
- influence diagrams
- incomplete information
- temporal difference
- multi agent
- function approximation
- state space
- learning agents
- computational complexity
- cooperative
- optimal policy
- dynamic programming
- learning algorithm
- neural network
- sensitivity analysis
- model free
- graphical models
- evolutionary algorithm