The StarCraft Multi-Agent Challenge

by   Mikayel Samvelyan, et al.

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:


page 1

page 4

page 5


Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning

Learning from datasets without interaction with environments (Offline Le...

Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning

In recent years we have seen fast progress on a number of benchmark prob...

Towards a Standardised Performance Evaluation Protocol for Cooperative MARL

Multi-agent reinforcement learning (MARL) has emerged as a useful approa...

The Partially Observable Asynchronous Multi-Agent Cooperation Challenge

Multi-agent reinforcement learning (MARL) has received increasing attent...

SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning

The availability of challenging benchmarks has played a key role in the ...

Scalable Multi-Agent Lab Framework for Lab Optimization

Autonomous materials research systems allow scientists to fail smarter, ...

Multi-Agent Pathfinding: Definitions, Variants, and Benchmarks

The MAPF problem is the fundamental problem of planning paths for multip...

Please sign up or login with your details

Forgot password? Click here to reset