{"type":"ScholarlyArticle","title":"Variational Offline Multi-agent Skill Discovery","authors":[{"name":"Jiayu Chen","slug":"jiayu-chen","given":"Jiayu","family":"Chen","affiliation":""},{"name":"Tian Lan","slug":"tian-lan","given":"Tian","family":"Lan","affiliation":""},{"name":"Vaneet Aggarwal","slug":"vaneet-aggarwal","given":"Vaneet","family":"Aggarwal","affiliation":""}],"abstract":"Skills are effective temporal abstractions established for sequential decision making, which enable efficient hierarchical learning for long-horizon tasks and facilitate multi-task learning through their transferability. Despite extensive research, research gaps remain in multi-agent scenarios, particularly for automatically extracting subgroup coordination patterns in a multi-agent task. In this case, we propose two novel auto-encoder schemes: VO-MASD-3D and VO-MASD-Hier, to simultaneously capture subgroup- and temporal-level abstractions and form multi-agent skills, which firstly solves the aforementioned challenge. An essential algorithm component of these schemes is a dynamic grouping function that can automatically detect latent subgroups based on agent interactions in a task. Further, our method can be applied to offline multi-task data, and the discovered subgroup skills can be transferred across relevant tasks without retraining. Empirical evaluations on StarCraft tasks indicate that our approach significantly outperforms existing hierarchical multi-agent reinforcement learning (MARL) methods. Moreover, skills discovered using our method can effectively reduce the learning difficulty in MARL scenarios with delayed and sparse reward signals. The codebase is available at: https://github.com/LucasCJYSDL/VOMASD.","doi":"10.24963/ijcai.2025/538","url":"https://ijcai.org/proceedings/2025/538","pdf":"https://ijcai.org/proceedings/2025/0538.pdf","markdown":"https://ijcai.org/proceedings/2025/538.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/538","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Machine Learning","track":"Main Track","number":538,"pages":{"first":4833,"last":4841},"keywords":["Agent-based and Multi-agent Systems: MAS: Multi-agent learning","Machine Learning: ML: Reinforcement learning","Machine Learning: ML: Multiagent Reinforcement Learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}