Market Overview

Google's Artificial Intelligence Algorithm Masters Video Games In A Matter Of Hours

Share:
Google's Artificial Intelligence Algorithm Masters Video Games In A Matter Of Hours
Related GOOG
AT&T Reportedly In Talks To Acquire AppNexus
Investors Appear To Like Small Caps Amid Continued Trade Worries
Redfin: The 'Everything' Of Real Estate (Seeking Alpha)
Related GOOGL
AT&T Reportedly In Talks To Acquire AppNexus
Instagram Announces IGTV For Its 1 Billion Monthly Active Users
Howard Marks Is Back And He Wants To Talk To You About ETFs, Passive Investing And 'Investing Without People' (Seeking Alpha)

In a recent publication in Nature, Google Inc (NASDAQ: GOOG) (NASDAQ: GOOGL)'s DeepMind artificial intelligence unit detailed the ability of its Q-network (DQN) algorithm to not just learn how to play video games from scratch, but determine how to beat the games in a matter of hours.

The paper detailed the algorithm's performance on 49 Atari 2600 video games, including Breakout, River Raid, Boxing and Enduro.

How DQN Works

DQN works by using only the raw screen pixels, the set of available actions and the game score as input. DeepMind founder Demis Hassabis was impressed by the algorithm's ability to master the wide range of games utilizing the same tuning parameters for each.

One of the unique properties of DQN that aids with its learning is its neural-like networks, including networks for reinforced learning.

Related Link: 20 Stocks That Sound Like Transformers

"Foremost among these was a neurobiologically inspired mechanism, termed ‘experience replay', whereby during the learning phase DQN was trained on samples drawn from a pool of stored episodes- a process physically realized in a brain structure called the hippocampus through the ultra-fast reactivation of recent experiences during rest periods (eg sleep)," Hassabis and co-author Dharshan Kumaran explained in a blog post.

DQN Versus Human Players

The algorithm performed with varying degrees of success on the range of games.

While DQN managed to perform as well as a human player on about half of the games, it struggled compared to human players in games such as Space Invaders because of the long-term strategy the game requires.

Will DQN Enslave Us All?

DeepMind was initially funded in part by Tesla Motors Inc (NASDAQ: TSLA) CEO Elon Musk, who later admitted he recognizes the potential danger in artificial intelligence. "There have been movies about this," Musk explained, "you know, like Terminator." 

According to DeepMind, the human race has nothing to fear from DQN. They envision the algorithm serving as an aide to humans by completing complex tasks such as planning a fun vacation.

Image credit: Juxi, Wikimedia

Posted-In: News Events Tech Best of Benzinga

 

Related Articles (GOOG + GOOGL)

View Comments and Join the Discussion!