Unreal-MAP: Unreal-Engine-Based General Platform for Multi-Agent Reinforcement Learning
This provides a user-friendly tool for MARL researchers to integrate algorithms with customized tasks, but it is incremental as it builds on existing engines and frameworks.
The authors tackled the lack of a general platform for multi-agent reinforcement learning (MARL) by proposing Unreal-MAP, an open-source platform based on Unreal Engine that enables users to create custom tasks and deploy state-of-the-art algorithms, with experimental analyses conducted on example tasks.
In this paper, we propose Unreal Multi-Agent Playground (Unreal-MAP), an MARL general platform based on the Unreal-Engine (UE). Unreal-MAP allows users to freely create multi-agent tasks using the vast visual and physical resources available in the UE community, and deploy state-of-the-art (SOTA) MARL algorithms within them. Unreal-MAP is user-friendly in terms of deployment, modification, and visualization, and all its components are open-source. We also develop an experimental framework compatible with algorithms ranging from rule-based to learning-based provided by third-party frameworks. Lastly, we deploy several SOTA algorithms in example tasks developed via Unreal-MAP, and conduct corresponding experimental analyses. We believe Unreal-MAP can play an important role in the MARL field by closely integrating existing algorithms with user-customized tasks, thus advancing the field of MARL.