The StarCraft Multi-Agent Challenge

By Mikayel Samvelyan, Tabish Rashid, Christian Schröder de Witt, Gregory Farquhar, Nantas Nardelli, Tim G. J. Rudner, Chia-Man Hung, Philip H. S. Torr, Jakob N. Foerster, Shimon Whiteson. 2019

1,262 citations recorded by the source corpus.

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. 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-the-art algorithms. 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.

Subfields: Artificial Intelligence, Management Science and Operations Research, LLM Agents & Tool Use, Reinforcement Learning, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Sergey Levine
  2. Yoshua Bengio
  3. Mohit Bansal
  4. Shimon Whiteson
  5. Quoc V. Le
  6. Ruslan Salakhutdinov
  7. Pieter Abbeel
  8. Jianfeng Gao

In Management Science and Operations Research

  1. Shimon Whiteson
  2. Filippos Christianos
  3. Stefano V. Albrecht
  4. Chongjie Zhang
  5. Wendelin Böhmer
  6. Georgios Papoudakis
  7. Tabish Rashid
  8. Christian Schröder de Witt

In LLM Agents & Tool Use

  1. Shimon Whiteson
  2. Wendelin Böhmer
  3. Chongjie Zhang
  4. Tabish Rashid
  5. Davood Hajinezhad
  6. Afshin Oroojlooyjadid
  7. Tonghan Wang
  8. Stefano V. Albrecht

In Reinforcement Learning

  1. Shimon Whiteson
  2. Sergey Levine
  3. Pieter Abbeel
  4. Chongjie Zhang
  5. Jakob N. Foerster
  6. Yuxi Li
  7. Tonghan Wang
  8. Christian Schröder de Witt

In Evaluation & Benchmarks

  1. Shimon Whiteson
  2. Bolei Zhou
  3. Antonio Torralba
  4. Wendelin Böhmer
  5. Sanja Fidler
  6. Chongjie Zhang
  7. Tabish Rashid
  8. Josh Tenenbaum

Citations in the corpus