Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games.
Shicong CenYuejie ChiSimon S. DuLin XiaoPublished in: CoRR (2022)
Keyphrases
- markov games
- markov decision processes
- markov decision process
- multiagent reinforcement learning
- reinforcement learning algorithms
- reinforcement learning
- control problems
- optimal policy
- state space
- multi agent
- multiagent systems
- policy iteration
- nash equilibrium
- stochastic games
- model free
- finite horizon
- cooperative
- infinite horizon
- dynamic programming
- average reward
- average cost
- function approximation
- convergence speed
- optimal stopping
- machine learning
- initial state
- multi agent systems
- transition probabilities
- optimal control
- random walk
- worst case