Decentralized Multi-Agent Reinforcement Learning for Continuous-Space Stochastic Games
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913285359534080 |
|---|---|
| author | Altabaa, Awni Yongacoglu, Bora Yüksel, Serdar |
| author_facet | Altabaa, Awni Yongacoglu, Bora Yüksel, Serdar |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_13539 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Decentralized Multi-Agent Reinforcement Learning for Continuous-Space Stochastic Games Altabaa, Awni Yongacoglu, Bora Yüksel, Serdar Machine Learning Computer Science and Game Theory 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. |
| title | Decentralized Multi-Agent Reinforcement Learning for Continuous-Space Stochastic Games |
| topic | Machine Learning Computer Science and Game Theory |
| url | https://arxiv.org/abs/2303.13539 |