SMAClite: A Lightweight Environment for Multi-Agent Reinforcement Learning
This provides a more accessible and efficient benchmark for MARL researchers, though it is incremental as it builds on the existing SMAC framework.
The authors tackled the lack of standard benchmarks in Multi-Agent Reinforcement Learning by introducing SMAClite, a lightweight, open-source environment that reproduces SMAC results while outperforming it in runtime speed and memory usage.
There is a lack of standard benchmarks for Multi-Agent Reinforcement Learning (MARL) algorithms. The Starcraft Multi-Agent Challenge (SMAC) has been widely used in MARL research, but is built on top of a heavy, closed-source computer game, StarCraft II. Thus, SMAC is computationally expensive and requires knowledge and the use of proprietary tools specific to the game for any meaningful alteration or contribution to the environment. We introduce SMAClite -- a challenge based on SMAC that is both decoupled from Starcraft II and open-source, along with a framework which makes it possible to create new content for SMAClite without any special knowledge. We conduct experiments to show that SMAClite is equivalent to SMAC, by training MARL algorithms on SMAClite and reproducing SMAC results. We then show that SMAClite outperforms SMAC in both runtime speed and memory.