RODE: Learning Roles to Decompose Multi-Agent Tasks
This addresses the challenge of scalable multi-agent learning in complex environments like StarCraft II, though it is incremental as it builds on existing role-based approaches.
The paper tackles the problem of efficiently discovering roles for scalable multi-agent reinforcement learning by decomposing joint action spaces based on action effects, resulting in outperforming state-of-the-art methods on 10 out of 14 StarCraft II scenarios and achieving rapid transfer to environments with three times the number of agents.
Role-based learning holds the promise of achieving scalable multi-agent learning by decomposing complex tasks using roles. However, it is largely unclear how to efficiently discover such a set of roles. To solve this problem, we propose to first decompose joint action spaces into restricted role action spaces by clustering actions according to their effects on the environment and other agents. Learning a role selector based on action effects makes role discovery much easier because it forms a bi-level learning hierarchy -- the role selector searches in a smaller role space and at a lower temporal resolution, while role policies learn in significantly reduced primitive action-observation spaces. We further integrate information about action effects into the role policies to boost learning efficiency and policy generalization. By virtue of these advances, our method (1) outperforms the current state-of-the-art MARL algorithms on 10 of the 14 scenarios that comprise the challenging StarCraft II micromanagement benchmark and (2) achieves rapid transfer to new environments with three times the number of agents. Demonstrative videos are available at https://sites.google.com/view/rode-marl .