Efficient Reinforcement Learning for Zero-Shot Coordination in Evolving Games
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909910411771904 |
|---|---|
| author | Hui, Bingyu Yu, Lebin Yao, Quanming Qu, Yunpeng Zhang, Xudong Wang, Jian |
| author_facet | Hui, Bingyu Yu, Lebin Yao, Quanming Qu, Yunpeng Zhang, Xudong Wang, Jian |
| contents | Zero-shot coordination(ZSC), a key challenge in multi-agent game theory, has become a hot topic in reinforcement learning (RL) research recently, especially in complex evolving games. It focuses on the generalization ability of agents, requiring them to coordinate well with collaborators from a diverse, potentially evolving, pool of partners that are not seen before without any fine-tuning. Population-based training, which approximates such an evolving partner pool, has been proven to provide good zero-shot coordination performance; nevertheless, existing methods are limited by computational resources, mainly focusing on optimizing diversity in small populations while neglecting the potential performance gains from scaling population size. To address this issue, this paper proposes the Scalable Population Training (ScaPT), an efficient RL training framework comprising two key components: a meta-agent that efficiently realizes a population by selectively sharing parameters across agents, and a mutual information regularizer that guarantees population diversity. To empirically validate the effectiveness of ScaPT, this paper evaluates it along with representational frameworks in Hanabi cooperative game and confirms its superiority. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_11083 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Efficient Reinforcement Learning for Zero-Shot Coordination in Evolving Games Hui, Bingyu Yu, Lebin Yao, Quanming Qu, Yunpeng Zhang, Xudong Wang, Jian Machine Learning Artificial Intelligence Zero-shot coordination(ZSC), a key challenge in multi-agent game theory, has become a hot topic in reinforcement learning (RL) research recently, especially in complex evolving games. It focuses on the generalization ability of agents, requiring them to coordinate well with collaborators from a diverse, potentially evolving, pool of partners that are not seen before without any fine-tuning. Population-based training, which approximates such an evolving partner pool, has been proven to provide good zero-shot coordination performance; nevertheless, existing methods are limited by computational resources, mainly focusing on optimizing diversity in small populations while neglecting the potential performance gains from scaling population size. To address this issue, this paper proposes the Scalable Population Training (ScaPT), an efficient RL training framework comprising two key components: a meta-agent that efficiently realizes a population by selectively sharing parameters across agents, and a mutual information regularizer that guarantees population diversity. To empirically validate the effectiveness of ScaPT, this paper evaluates it along with representational frameworks in Hanabi cooperative game and confirms its superiority. |
| title | Efficient Reinforcement Learning for Zero-Shot Coordination in Evolving Games |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2511.11083 |