DeepMind: Google's artificial intelligence learns to play Quake III Arena

Offtopic discussion forum.
User avatar
imprecise
User lv5
User lv5
Posts: 337
Joined: Mon May 04, 2020 17:30
in-game nick: imprecise
Location: France

DeepMind: Google's artificial intelligence learns to play Quake III Arena

Post by imprecise »

DEEPMIND https://deepmind.com/blog/article/captu ... ag-science

Mastering the strategy, tactical understanding, and team play involved in multiplayer video games represents a critical challenge for AI research. In our latest paper, now published in the journal Science, we present new developments in reinforcement learning, resulting in human-level performance in Quake III Arena Capture the Flag. This is a complex, multi-agent environment and one of the canonical 3D first-person multiplayer games. The agents successfully cooperate with both artificial and human teammates, and demonstrate high performance even when trained with reaction times comparable to human players. Furthermore, we show how these methods have managed to scale beyond research Capture the Flag environments to the full game of Quake III Arena.

more info, explanations, images and videos on the site

Image
An early test tournament with humans playing CTF with and against trained agents and other humans
"My ability to concentrate is so short that ... Oh a butterfly !"
PacMan
User lv5
User lv5
Posts: 1187
Joined: Sat Oct 21, 2017 16:09
in-game nick: PacMan.EZ
Location: u.k

Re: DeepMind: Google's artificial intelligence learns to play Quake III Arena

Post by PacMan »

Miroslav probably still beat them lol
User avatar
Dr.GreenThumb
User lv4
User lv4
Posts: 207
Joined: Thu May 30, 2019 1:06
in-game nick: Dr.GreenThumb
Location: The Netherlands

Re: DeepMind: Google's artificial intelligence learns to play Quake III Arena

Post by Dr.GreenThumb »

Interesting, thank you for ths share.