| Autor: |
Altabaa, Awni, Yongacoglu, Bora, Yüksel, Serdar |
| Rok vydání: |
2023 |
| Předmět: |
|
| Zdroj: |
2023 American Control Conference (ACC), San Diego, CA, USA, 2023, pp. 72-77 |
| Druh dokumentu: |
Working Paper |
| DOI: |
10.23919/ACC55779.2023.10155828 |
| Popis: |
Stochastic games are a popular framework for studying multi-agent reinforcement learning (MARL). Recent advances in MARL have focused primarily on games with finitely many states. In this work, we study multi-agent learning in stochastic games with general state spaces and an information structure in which agents do not observe each other's actions. In this context, we propose a decentralized MARL algorithm and we prove the near-optimality of its policy updates. Furthermore, we study the global policy-updating dynamics for a general class of best-reply based algorithms and derive a closed-form characterization of convergence probabilities over the joint policy space. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
