DeepMind Has A Superhuman Level Quake 3 AI Team! 🚀

preview_player
Показать описание

The paper "Human-level performance in first-person multiplayer games with population-based deep reinforcement learning" and its corresponding blog post are available here:

Crypto and PayPal links are available below. Thank you very much for your generous support!
Bitcoin: 13hhmJnLEzwXgmgJN7RB6bWVdT7WkrFAHh
Ethereum: 0x002BB163DfE89B7aD0712846F1a1E53ba6136b5A
LTC: LM8AUh5bGcNgzq6HaV1jeaJrFvmKxxgiXg

We would like to thank our generous Patreon supporters who make Two Minute Papers possible:
313V, Andrew Melnychuk, Angelos Evripiotis, Brian Gilman, Christian Ahlin, Christoph Jadanowski, Dennis Abts, Emmanuel, Eric Haddad, Esa Turkulainen, Geronimo Moralez, Kjartan Olason, Lorin Atzberger, Marten Rauschenberg, Michael Albrecht, Michael Jensen, Morten Punnerud Engelstad, Nader Shakerin, Owen Skarpness, Rafael Harutyuynyan, Raul Araújo da Silva, Rob Rowe, Robin Graham, Ryan Monsurate, Shawn Azman, Steef, Steve Messina, Sunil Kim, Thomas Krcmar, Torsten Reil, Zach Boldyga.

Crypto and PayPal links are available below. Thank you very much for your generous support!
Bitcoin: 13hhmJnLEzwXgmgJN7RB6bWVdT7WkrFAHh
Ethereum: 0x002BB163DfE89B7aD0712846F1a1E53ba6136b5A
LTC: LM8AUh5bGcNgzq6HaV1jeaJrFvmKxxgiXg

Two Minute Papers Merch:

Károly Zsolnai-Fehér's links:

#DeepMind #Quake #Quake3
Рекомендации по теме
Комментарии
Автор

Training an AI team at a shooter game - I don’t see any way how this could go wrong

KRTB
Автор

I love how you are able to instill suspense when narrating AI results.

thomassynths
Автор

Really exciting because of the sparse internal rewards and long term planning. A step towards AI agents that are useful in real life.

MobyMotion
Автор

I was really hoping to see an AI that mastered bunny hopping and item control in standard duel mode.

eggory
Автор

Karoly....I have something to admit. I'm not a scholar.

jasonjasonjasonjasonjason
Автор

*cracks open a monster*

yep, quake was a good game

lucid
Автор

This is incredible work! These developments, for example AI developing its own definition of a reward, are exactly what are needed for more complex AI agents. I was thinking the other day about how rewards would be defined for complex AI problems, and realized that humans can use context to understand whether or not they are succeeding, and use this to determine the actions they need to take to do so. I am looking forward to what this research leads to!

diamondguy
Автор

This shit is progressing so quickly by the time I graduate we'll have a singularity before I can even work on it. Dammit hehe

ziquaftynny
Автор

We need this as an official Quake III Arena mod

ermonski
Автор

This sounds like a big jump. It's all happening so fast, it's hard to believe. Good thing I found this channel. You just can't keep up with the speed of progress otherwise.

Lugmillord
Автор

Damn this is fucking amazing. With this level of genetic learning, the only obstacle to apply these concepts to real life (e.g. self-driving cars) seems to be just the "mapping" from our reality to "computer reality".

TheDarkever
Автор

I love to see AI applied to games! You inspire me to make my own AI videos!

PandoraMakesGames
Автор

0:41 *Red ball at the bottom spinning in a circle* "AI has to learn general concepts"

nova_vista
Автор

Imagine walking by google headqarters, "This is our FTW!! section ..."

Minedodge
Автор

Amazing! FTW this stuff is advancing every week! Incredible. At this rate I won't be able to hold onto my papers anymore!

markonfilms
Автор

I am excited to see studies on AIs training humans

SmashedHatProject
Автор

I want to see the actual gameplay. Also want to see a bot that can duel in Quake. I'm sure the accuracy would have to be artificially reduced of course or it would just be using 100% rail accuracy to destroy the human. I want to see how it strafe jumps though

mitsuracer
Автор

the best channel ever!!! please do more practical stuff too! :)

not_a_human_being
Автор

ty for the vid, I'm going to attempt reading the paper. really wish my school would teach this. this is a great opener for a machine learning course imo. just swap out the game for your first class project

spankymebottom
Автор

This needs to be a downloadable mod for Quake 3

ermonski