Near-Optimal Policy Optimization for Correlated Equilibrium in General-Sum Markov Games.
Yang CaiHaipeng LuoChen-Yu WeiWeiqiang ZhengPublished in: AISTATS (2024)
Keyphrases
- optimal policy
- markov decision processes
- dynamic programming
- decision problems
- special case
- infinite horizon
- reinforcement learning
- state space
- sufficient conditions
- finite horizon
- long run
- reinforcement learning algorithms
- state dependent
- correlated equilibrium
- multistage
- multi agent
- markov decision process
- finite state
- partially observable markov decision processes
- average cost
- function approximation
- resource allocation