Massively Multiagent Minigames for Training Generalist Agents
Massively Multiagent Minigames for Training Generalist Agents
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 …