Global Convergence of Localized Policy Iteration in Networked Multi-Agent Reinforcement Learning.
Yizhou ZhangGuannan QuPan XuYiheng LinZaiwei ChenAdam WiermanPublished in: SIGMETRICS (Abstracts) (2023)
Keyphrases
- multi agent reinforcement learning
- global convergence
- policy iteration
- convergence rate
- reinforcement learning
- markov decision processes
- convergence speed
- model free
- convergence analysis
- optimization methods
- stochastic games
- global optimum
- optimal policy
- step size
- temporal difference
- multi agent
- fixed point
- average reward
- infinite horizon
- function approximation
- state space
- reinforcement learning algorithms
- machine learning
- finite state
- markov decision process
- multi agent systems
- cooperative
- linear programming
- learning algorithm
- optimization method
- optimization algorithm
- average cost
- evolutionary algorithm
- learning process