TonghanWang / RODELinks

Codes accompanying the paper "RODE: Learning Roles to Decompose Multi-Agent Tasks (ICLR 2021, https://arxiv.org/abs/2010.01523). RODE is a scalable role-based multi-agent learning method which effectively discovers roles based on joint action space decomposition according to action effects, establishing a new state of the art on the StarCraft mu…
79Updated 10 months ago

Alternatives and similar repositories for RODE

Users that are interested in RODE are comparing it to the libraries listed below

Sorting: