Massively Multiagent Minigames For Training Generalist Agents

Abstract

We present Meta MMO, a collection of many-agent minigames for use as a reinforcement learning benchmark. Meta MMO is built on top of Neural MMO, a massively multiagent environment that has been the subject of two previous NeurIPS competitions. Our work expands Neural MMO with several computationally efficient minigames. We explore generalization across Meta MMO by learning to play several minigames with a single set of weights. We release the environment, baselines, and training code under the MIT license. We hope that Meta MMO will spur additional progress on Neural MMO and, more generally, will serve as a useful benchmark for many-agent generalization.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychoe2024massively

Related papers

• Neural MMO V1.3: A Massively Multiagent Game Environment For Training And Evaluating Neural Networks (2020)0.00
• Neural MMO 2.0: A Massively Multi-task Addition To Massively Multi-agent Learning (2023)0.00
• Benchmarking Robustness And Generalization In Multi-agent Systems: A Case Study On Neural MMO (2023)0.00
• The Neurips 2022 Neural MMO Challenge: A Massively Multiagent Competition With Specialization And Trade (2023)0.00
• Learning Meta Representations For Agents In Multi-agent Reinforcement Learning (2021)0.00
• Beyond Playtesting: A Generative Multi-agent Simulation System For Massively Multiplayer Online Games (2025)0.00
• Alchemy: A Benchmark And Analysis Toolkit For Meta-reinforcement Learning Agents (2021)0.00
• Mini Honor Of Kings: A Lightweight Environment For Multi-agent Reinforcement Learning (2024)3.42