Decentralized Learning for Optimality in Stochastic Dynamic Teams and Games with Local Control and Global State Information
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2019
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916178110185472 |
|---|---|
| author | Yongacoglu, Bora Arslan, Gürdal Yüksel, Serdar |
| author_facet | Yongacoglu, Bora Arslan, Gürdal Yüksel, Serdar |
| contents | Stochastic dynamic teams and games are rich models for decentralized systems and challenging testing grounds for multi-agent learning. Previous work that guaranteed team optimality assumed stateless dynamics, or an explicit coordination mechanism, or joint-control sharing. In this paper, we present an algorithm with guarantees of convergence to team optimal policies in teams and common interest games. The algorithm is a two-timescale method that uses a variant of Q-learning on the finer timescale to perform policy evaluation while exploring the policy space on the coarser timescale. Agents following this algorithm are "independent learners": they use only local controls, local cost realizations, and global state information, without access to controls of other agents. The results presented here are the first, to our knowledge, to give formal guarantees of convergence to team optimality using independent learners in stochastic dynamic teams and common interest games. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1903_05812 |
| institution | arXiv |
| publishDate | 2019 |
| record_format | arxiv |
| spellingShingle | Decentralized Learning for Optimality in Stochastic Dynamic Teams and Games with Local Control and Global State Information Yongacoglu, Bora Arslan, Gürdal Yüksel, Serdar Optimization and Control Stochastic dynamic teams and games are rich models for decentralized systems and challenging testing grounds for multi-agent learning. Previous work that guaranteed team optimality assumed stateless dynamics, or an explicit coordination mechanism, or joint-control sharing. In this paper, we present an algorithm with guarantees of convergence to team optimal policies in teams and common interest games. The algorithm is a two-timescale method that uses a variant of Q-learning on the finer timescale to perform policy evaluation while exploring the policy space on the coarser timescale. Agents following this algorithm are "independent learners": they use only local controls, local cost realizations, and global state information, without access to controls of other agents. The results presented here are the first, to our knowledge, to give formal guarantees of convergence to team optimality using independent learners in stochastic dynamic teams and common interest games. |
| title | Decentralized Learning for Optimality in Stochastic Dynamic Teams and Games with Local Control and Global State Information |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/1903.05812 |