Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games.
Stefanos LeonardosWill OvermanIoannis PanageasGeorgios PiliourasPublished in: ICLR (2022)
Keyphrases
- global convergence
- multi agent
- policy gradient
- convergence rate
- optimization methods
- single agent
- global optimum
- convergence speed
- reinforcement learning
- gradient method
- markov chain
- multi agent systems
- optimization method
- game theoretic
- simulated annealing
- stochastic games
- function approximation
- decision problems
- multiple agents
- nash equilibria
- machine learning