Machines are already capable of winning humans in video games

Google researchers Deep Mind get their artificial agents play and win in video games without human intervention, something impossible so far.

Researchers from Deep Mind, Google's artificial intelligence (AI) subsidiary, have made their AI agents able to play and win an online multiplayer game, something impossible to date, and which involves cooperating and competing with others. players.

According to a study published today in Science, AI has demonstrated an "amazing ability" to develop and use strategies, learned independently, without human intervention.

The method used by the company, which was acquired by Google in 2014, is the reinforcement of learning (Reinforcement Learning) and has been used previously so that other intelligences learn to play games like Go or shogi -more complex than chess- .

This method had demonstrated its success in first-person games -with a single player-, and two -like chess or Go-, but until now it had not broken the barrier of the multiplayer stage, where elements such as the game in team and the competition against more than one opponent.

The video game with which this feat has been demonstrated is "Quake III Arena Capture the Flag", a first-person shooter.

The study shows that the Google AI can play at the level of a player of flesh and blood, and beat both other artificial intelligence and human players.

The artificial intelligence involved in the study were not trained or received information about the game or the players, but learned from their own experience playing, the score obtained and what they "saw" in the pixels on the screen.

The generated artificial intelligence learned to play from thousands of games that were developed between them and in randomly generated scenarios.