Gap-Dependent Bounds for Two-Player Markov Games.
Zehao DouZhuoran YangZhaoran WangSimon S. DuPublished in: AISTATS (2022)
Keyphrases
- markov games
- reinforcement learning algorithms
- reinforcement learning
- nash equilibrium
- markov decision processes
- multiagent reinforcement learning
- state space
- model free
- upper bound
- stochastic games
- lower bound
- worst case
- function approximation
- game theory
- temporal difference
- game theoretic
- dynamic environments
- markov decision process
- machine learning
- reward function
- nash equilibria
- cooperative
- learning algorithm
- optimal policy
- mobile robot
- single agent
- multi agent