DeepMind's new gamer AI goes 'for the win' in multiplayer first-person video games

May 30, 2019

DeepMind researchers have taught artificially intelligent gamers to play a popular 3D multiplayer first-person video game with human-like skills - a previously insurmountable task. The reinforcement learning-trained AI agents demonstrate an uncanny ability to develop and use independently learned high-level strategies to compete and cooperate in the game environment. Reinforcement learning (RL), a method used to train artificially intelligent agents, has shown success in producing artificially intelligent players that are able to navigate increasingly complex single-player environments. These agents can also achieve superhuman mastery in competitive two-player turn-based games, like chess and Go. However, the ability to play multiplayer games, particularly those that involve teamwork and interaction between multiple independent players, has eluded the capabilities of AI systems to date. Here, Max Jaderberg and colleagues present a RL-trained AI agent that can achieve human-level performance in the seminal multiplayer 3D first-person video game, Quake III Arena Capture the Flag. In contrast to previous studies, where AI agents are supplied with "knowledge" about the game environment or status of other players, Jaderberg et al.'s RL approach ensured that each agent learned independently from its own experience using only what it could "see" (pixels) and the game's score. Pitted against one another, a population of AI agents learned to play the game over thousands of matches in randomly generated environments. According to the authors, over time, the agents independently developed surprisingly high-level strategies, not unlike those used by skilled human players. What's more, in games with human players, the agents outperformed human opponents, even when the agents' reaction times were slowed down to human levels. Furthermore, the agents were also able to form and cooperate in ad hoc computer and human teams.
-end-


American Association for the Advancement of Science

Related Game Articles from Brightsurf:

Researchers exploit weaknesses of master game bots
Researchers at Penn State designed an algorithm to train an adversarial bot, which was able to automatically discover and exploit weaknesses of master game bots driven by reinforcement learning algorithms.

Leaving money on the table to stay in the game
Unlike businesses or governments, organisms can't go into evolutionary debt -- there is no borrowing one's way back from extinction.

A memory game could help us understand brain injury
A Boston University team created a memory game for mice in order to examine the function of two different brain areas that process information about the sensation of touch and the memory of previous events.

Is video game addiction real?
A recent six-year study, the longest study ever done on video game addiction, found that about 90% of gamers do not play in a way that is harmful or causes negative long-term consequences.

Kids eat more calories in post-game snacks than they burn during the game
A new study led by Brigham Young University public health researchers finds the number of calories kids consume from post-game snacks far exceeds the number of calories they actually burn playing in the game.

Can exercise improve video game performance?
Time spent playing video games is often seen as time stolen from physical activities.

Computer game may help to predict reuse of opioids
A computer betting game can help predict the likelihood that someone recovering from opioid addiction will reuse the pain-relieving drugs, a new study shows.

Get your game face on: Study finds it may help
Could putting on a serious face in preparation for competition actually impact performance?

Game changer: New chemical keeps plants plump
A UC Riverside-led team has created a chemical to help plants hold onto water, which could stem the tide of massive annual crop losses from drought and help farmers grow food despite a changing climate.

Big game hunting for a more versatile catalyst
For the first time, researchers at Harvard University and Cornell University have discovered exactly how a reactive copper-nitrene catalyst works, a finding that could revolutionize how chemical industries produce everything from pharmaceuticals to household goods.

Read More: Game News and Game Current Events
Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.