Neural MMO v1.3: A Massively Multiagent Game Environment for Training and Evaluating Neural Networks
arXiv:2001.12004
Abstract
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.
References in corpus (10)
- Playing Atari with Deep Reinforcement Learning
- Human-level performance in first-person multiplayer games with population-based deep reinforcement learning
- Emergent Tool Use From Multi-Agent Autocurricula
- Mean Field Multi-Agent Reinforcement Learning
- Ray: A Distributed Framework for Emerging AI Applications
- Emergent Complexity via Multi-Agent Competition
- Gotta Learn Fast: A New Benchmark for Generalization in RL
- Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents
- MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence
- A Study of AI Population Dynamics with Million-agent Reinforcement Learning