UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Human-level performance in 3D multiplayer games with population-based reinforcement learning

Jaderberg, M; Czarnecki, WM; Dunning, I; Marris, L; Lever, G; Castaneda, AG; Beattie, C; ... Graepel, T; + view all (2019) Human-level performance in 3D multiplayer games with population-based reinforcement learning. Science , 364 (6443) pp. 859-865. 10.1126/science.aau6249. Green open access

[thumbnail of Graepel_Human-level performance in 3D multiplayer games with population-based reinforcement learning_AAM.pdf]
Preview
Text
Graepel_Human-level performance in 3D multiplayer games with population-based reinforcement learning_AAM.pdf - Accepted Version

Download (9MB) | Preview

Abstract

Reinforcement learning (RL) has shown great success in increasingly complex single-agent environments and two-player turn-based games. However, the real world contains multiple agents, each learning and acting independently to cooperate and compete with other agents. We used a tournament-style evaluation to demonstrate that an agent can achieve human-level performance in a three-dimensional multiplayer first-person video game, Quake III Arena in Capture the Flag mode, using only pixels and game points scored as input. We used a two-tier optimization process in which a population of independent RL agents are trained concurrently from thousands of parallel matches on randomly generated environments. Each agent learns its own internal reward signal and rich representation of the world. These results indicate the great potential of multiagent reinforcement learning for artificial intelligence research.

Type: Article
Title: Human-level performance in 3D multiplayer games with population-based reinforcement learning
Open access status: An open access version is available from UCL Discovery
DOI: 10.1126/science.aau6249
Publisher version: https://doi.org/10.1126/science.aau6249
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Science & Technology, Multidisciplinary Sciences, Science & Technology - Other Topics, TIME, GO
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10076318
Downloads since deposit
117Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item