The Multi-Agent Reinforcement Learning in MalmÖ (MARLÖ) Competition

01/23/2019
by   Diego Pérez-Liébana, et al.
12

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 MalmÖ (MARLÖ) 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/17/2019

Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence

Learning agents that are not only capable of taking tests but also innov...
research
02/14/2020

Extended Markov Games to Learn Multiple Tasks in Multi-Agent Reinforcement Learning

The combination of Formal Methods with Reinforcement Learning (RL) has r...
research
09/04/2022

Learning to Deceive in Multi-Agent Hidden Role Games

Deception is prevalent in human social settings. However, studies into t...
research
01/19/2023

Multi-Agent Interplay in a Competitive Survival Environment

Solving hard-exploration environments in an important challenge in Reinf...
research
06/09/2021

Deception in Social Learning: A Multi-Agent Reinforcement Learning Perspective

Within the framework of Multi-Agent Reinforcement Learning, Social Learn...
research
09/10/2022

Cooperation and Competition: Flocking with Evolutionary Multi-Agent Reinforcement Learning

Flocking is a very challenging problem in a multi-agent system; traditio...
research
09/30/2020

PettingZoo: Gym for Multi-Agent Reinforcement Learning

This paper introduces PettingZoo, a library of diverse sets of multi-age...

Please sign up or login with your details

Forgot password? Click here to reset