Breaking the Curse of Multiagency: Provably Efficient Decentralized Multi-Agent RL with Function Approximation.
Yuanhao WangQinghua LiuYu BaiChi JinPublished in: COLT (2023)
Keyphrases
- function approximation
- reinforcement learning
- multi agent
- temporal difference
- temporal difference learning
- model free
- radial basis function
- temporal difference learning algorithms
- tile coding
- learning tasks
- machine learning
- state space
- reinforcement learning algorithms
- function approximators
- multi agent systems
- feature selection
- rl algorithms