Arena: a toolkit for Multi-Agent Reinforcement Learning
This toolkit addresses the complexity and customization challenges in MARL research, making it easier for researchers to experiment with different scenarios, though it is incremental as it builds on existing concepts like OpenAI Gym Wrappers.
The authors introduced Arena, a toolkit for multi-agent reinforcement learning (MARL) research that provides a modular design called Interface to simplify customizing observations, rewards, actions, and agent interactions, and it supports various popular MARL platforms like StarCraft II and Pommerman.
We introduce Arena, a toolkit for multi-agent reinforcement learning (MARL) research. In MARL, it usually requires customizing observations, rewards and actions for each agent, changing cooperative-competitive agent-interaction, and playing with/against a third-party agent, etc. We provide a novel modular design, called Interface, for manipulating such routines in essentially two ways: 1) Different interfaces can be concatenated and combined, which extends the OpenAI Gym Wrappers concept to MARL scenarios. 2) During MARL training or testing, interfaces can be embedded in either wrapped OpenAI Gym compatible Environments or raw environment compatible Agents. We offer off-the-shelf interfaces for several popular MARL platforms, including StarCraft II, Pommerman, ViZDoom, Soccer, etc. The interfaces effectively support self-play RL and cooperative-competitive hybrid MARL. Also, Arena can be conveniently extended to your own favorite MARL platform.