The Multi-Agent Reinforcement Learning in Malm\"O (MARL\"O) Competition

TL;DR

The MARL"O competition challenges researchers to develop scalable multi-agent reinforcement learning algorithms capable of generalizing across diverse 3D games and opponent types, advancing towards Artificial General Intelligence.

Contribution

This paper introduces the MARL"O competition, a new benchmark for multi-agent reinforcement learning in diverse 3D games to promote research on general agents.

Findings

Addresses scalability issues in multi-agent learning

Encourages development of general agents across multiple games

Fosters progress towards Artificial General Intelligence

Abstract

Learning in multi-agent scenarios is a fruitful research direction, but current approaches still show scalability problems in multiple games with general reward settings and different opponent types. The Multi-Agent Reinforcement Learning in Malm\"O (MARL\"O) competition is a new challenge that proposes research in this domain using multiple 3D games. The goal of this contest is to foster research in general agents that can learn across different games and opponent types, proposing a challenge as a milestone in the direction of Artificial General Intelligence.