Getting started with the environment
Before we jump into our first MARL example, let’s look at the environment we can use. If you want to play with MARL, your choice is a bit limited. All the environments that come with Gym support only one agent. There are some patches for Atari Pong, to switch it into two-player mode, but they are not standard and are an exception rather than the rule.
DeepMind, together with Blizzard, has made StarCraft II publicly available ( https://github.com/deepmind/pysc2) and makes for a very interesting and challenging environment for experimentation. However, for somebody who is taking their first steps in MARL, it might be too complex. In that regard, I have found the MAgent environment, originally developed by Geek.AI, to be perfectly suitable; it is simple and fast and has minimal dependency, but it still allows you to simulate different multi-agent scenarios for experimentation. It doesn’t provide a Gym-compatible API, but we...
