Massively Multiagent Minigames for Training Generalist Agents
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 36 of its 54 references that are in the map. First posted on arXiv 7 Jun 2024.
Builds on
36 of 54 references.
References · 36
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
- 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
- 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
- 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
- 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 903
- 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 866
- 2019The StarCraft Multi-Agent Challengecited by 589
- 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 478
- 2019Emergent Tool Use From Multi-Agent Autocurriculacited by 308
- 2020Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?cited by 281
- 2017Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agentscited by 267
24 more
- 2020Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Designcited by 260
- 2017Emergence of Grounded Compositional Language in Multi-Agent Populationscited by 257
- 2020PettingZoo: Gym for Multi-Agent Reinforcement Learningcited by 209
- 2020The NetHack Learning Environmentcited by 196
- 2020Prioritized Level Replaycited by 190
- 2019Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutionscited by 182
- 2021Open-Ended Learning Leads to Generally Capable Agentscited by 177
- 2018Multi-task Deep Reinforcement Learning with PopArtcited by 138
- 2023Human-Timescale Adaptation in an Open-Ended Task Spacecited by 136
- 2018Generalization and Regularization in DQNcited by 117
- 2021Replay-Guided Adversarial Environment Designcited by 108
- 2021Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Potcited by 97
- 2021MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Researchcited by 96
- 2024Scaling Instructable Agents Across Many Simulated Worldscited by 67
- 2022VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learningcited by 63
- 2023XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAXcited by 54
- 2022Exploration via Elliptical Episodic Bonusescited by 51
- 2019Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agentscited by 42
- 2021The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priorscited by 40
- 2021Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraftcited by 34
- 2022MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learnedcited by 26
- 2021Megaverse: Simulating Embodied Agents at One Million Experiences per Secondcited by 19
- 2022Grounding Aleatoric Uncertainty for Unsupervised Environment Designcited by 16
- 2023Neural MMO 2.0: A Massively Multi-task Addition to Massively Multi-agent Learningcited by 9
Built on by
Not cited yet.