Neural MMO v1.3: A Massively Multiagent Game Environment for Training and Evaluating Neural Networks
This provides a new platform for studying multiagent AI, addressing complexities not well-modeled by other game genres, though it is incremental in building on existing game-based research.
The authors tackled the lack of environments for multiagent intelligence research by introducing Neural MMO, a massively multiagent game environment inspired by MMORPGs, and demonstrated that standard policy gradient methods can learn emergent exploration and specialization behaviors in this setting.
Progress in multiagent intelligence research is fundamentally limited by the number and quality of environments available for study. In recent years, simulated games have become a dominant research platform within reinforcement learning, in part due to their accessibility and interpretability. Previous works have targeted and demonstrated success on arcade, first person shooter (FPS), real-time strategy (RTS), and massive online battle arena (MOBA) games. Our work considers massively multiplayer online role-playing games (MMORPGs or MMOs), which capture several complexities of real-world learning that are not well modeled by any other game genre. We present Neural MMO, a massively multiagent game environment inspired by MMOs and discuss our progress on two more general challenges in multiagent systems engineering for AI research: distributed infrastructure and game IO. We further demonstrate that standard policy gradient methods and simple baseline models can learn interesting emergent exploration and specialization behaviors in this setting.