Timezone: »

 
Poster
ROMA: Multi-Agent Reinforcement Learning with Emergent Roles
Tonghan Wang · Heng Dong · Victor Lesser · Chongjie Zhang

Thu Jul 16 09:00 AM -- 09:45 AM & Thu Jul 16 08:00 PM -- 08:45 PM (PDT) @ Virtual
in Poster Session 44 »

The role concept provides a useful tool to design and understand complex multi-agent systems, which allows agents with a similar role to share similar behaviors. However, existing role-based methods use prior domain knowledge and predefine role structures and behaviors. In contrast, multi-agent reinforcement learning (MARL) provides flexibility and adaptability, but less efficiency in complex tasks. In this paper, we synergize these two paradigms and propose a role-oriented MARL framework (ROMA). In this framework, roles are emergent, and agents with similar roles tend to share their learning and to be specialized on certain sub-tasks. To this end, we construct a stochastic role embedding space by introducing two novel regularizers and conditioning individual policies on roles. Experiments show that our method can learn specialized, dynamic, and identifiable roles, which help our method push forward the state of the art on the StarCraft II micromanagement benchmark. Demonstrative videos are available at https://sites.google.com/view/romarl/.

Keywords: Deep Reinforcement Learning · Multiagent Learning · Planning, Control, and Multiagent Learning
[ Slides] 

Author Information

Tonghan Wang (Tsinghua University)
Heng Dong (Tsinghua)
Victor Lesser (UMASS)
Chongjie Zhang (Tsinghua University)

More from the Same Authors