Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents

By Joseph Suarez, Yilun Du, Phillip Isola, Igor Mordatch. 2019

92 citations recorded by the source corpus.

The emergence of complex life on Earth is often attributed to the arms race that ensued from a huge number of organisms all competing for finite resources. We present an artificial intelligence research environment, inspired by the human game genre of MMORPGs (Massively Multiplayer Online Role-Playing Games, a.k.a. MMOs), that aims to simulate this setting in microcosm. As with MMORPGs and the real world alike, our environment is persistent and supports a large and variable number of agents. Our environment is well suited to the study of large-scale multiagent interaction: it requires that agents learn robust combat and navigation policies in the presence of large populations attempting to do the same. Baseline experiments reveal that population size magnifies and incentivizes the development of skillful behaviors and results in agents that outcompete agents trained in smaller populations. We further show that the policies of agents with unshared weights naturally diverge to fill different niches in order to avoid competition.

Subfields: Artificial Intelligence, Sociology and Political Science

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Sociology and Political Science

Citations in the corpus

Action Semantics Network: Considering the Effects of Actions in Multiagent Systems (2019, methodology): “…DRL algorithms to boost its learning performance; 3) experimental results ∗ on StarCraft II micromanagement (Samvelyan et al., 2019) and Neural MMO (Suarez et al., 2019) show our ASN leads to better performance compared with state-of-the-art approaches in terms of both convergence speed and…”
A survey and critique of multiagent deep reinforcement learning (2018, methodology): “dent PPO learners. MuJoCo Multiagent Soccer [305] uses the MuJoCo physics engine [199]. The environment simulates a 2 vs. 2 soccer game with agents having a 3-dimensional action space.45 Neural MMO [306] is a research platform46 inspired by the human game genre of Massively Multiplayer Online (MMO) ”
Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence (2019, background): “2019), surviving (Suarez et al. 2019), and interaction (Wu et al.”
Building Cooperative Embodied Agents Modularly with Large Language Models (2023, background): “Our contribution includes: et al., 2019; Samvelyan et al., 2019; Suarez et al., 2019; Baker et al., 2019; Bard et al., 2020).”
Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration (2020, background): “There has been a large body of platforms for various multi-agent tasks (Jaderberg et al., 2019; Samvelyan et al., 2019; OpenAI, 2018; Lowe et al., 2017; Resnick et al., 2018; Shu & Tian, 2018; Carroll et al., 2019; Suarez et al., 2019; Baker et al., 2019; Bard et al., 2020).”