Multiplayer Support for the Arcade Learning Environment
This work addresses a gap for reinforcement learning researchers by enabling multiplayer game experiments, but it is incremental as it extends an existing library without introducing new methods.
The authors tackled the lack of multiplayer support in the Arcade Learning Environment (ALE) by developing a publicly available extension that enables programmatic interfacing with multiplayer Atari 2600 games, integrating it with PettingZoo for a Gym-like interface and providing experimental baselines.
The Arcade Learning Environment ("ALE") is a widely used library in the reinforcement learning community that allows easy programmatic interfacing with Atari 2600 games, via the Stella emulator. We introduce a publicly available extension to the ALE that extends its support to multiplayer games and game modes. This interface is additionally integrated with PettingZoo to allow for a simple Gym-like interface in Python to interact with these games. We additionally introduce experimental baselines for all environments included.