The StarCraft Multi-Agent Challenge

Conference item

In the last few years, deep multi-agent reinforcement learning (RL) has become a highly active area of research. A particularly challenging class of problems in this area is partially observable, cooperative, multi-agent learning, in which teams of agents must learn to coordinate their behaviour while conditioning only on their private observations. This is an attractive research area since such problems are relevant to a large number of real-world systems and are also more amenable to evaluation than general-sum problems. Standardised environments such as the ALE and MuJoCo have allowed single-agent RL to move beyond toy domains, such as grid worlds. However, there is no comparable benchmark for cooperative multi-agent RL. As a result, most papers in this field use one-off toy problems, making it difficult to measure real progress. In this paper, we propose the StarCraft Multi-Agent Challenge (SMAC) as a benchmark problem to fill this gap.1 SMAC is based on the popular real-time strategy game StarCraft II and focuses on micromanagement challenges where each unit is controlled by an independent agent that must act based on local observations. We offer a diverse set of challenge maps and recommendations for best practices in benchmarking and evaluations. We also open-source a deep multi-agent RL learning framework including state-of-theart algorithms.2 We believe that SMAC can provide a standard benchmark environment for years to come. Videos of our best agents for several SMAC scenarios are available at: https://youtu.be/VZ7zmQ_obZ0.

Authors: Mikayel Samvelyan; Tabish Rashid; Christian Schroeder de Witt; Gregory Farquhar; Nantas Nardelli

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: International Foundation for Autonomous Agents and Multiagent Systems
• Host title: Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems
• Volume: 4
• Pages: 2186-2188
• Publication date: 2019-10-01
• Acceptance date: 2019-10-01
• Event title: Conference on Autonomous Agents and MultiAgent Systems
• Event location: Montréal, Canada
• Event website: http://aamas2019.encs.concordia.ca/
• Event start date: 2019-05-13
• Event end date: 2019-05-17
• ISSN: 2523-5699
• ISBN: 978-1-4503-6309-9
• Keywords: Reinforcement Learning; StarCraft; Multi-Agent Learning; FFR