A new AI is under development by Google's artificial intelligence company , and it's outperforming humans in 57 Atari games.
DeepMind has been attempting to create an algorithm tha♌t learns by itself and demonstrate humanli🏅ke performance in a wide variety of tasks. Enter Agent57 - a learning algorithm and AI agent that's blowing people's socks off.
As observed by this year, Agent57 learned how to play 57 Atari games on a superhuman level. It literally played all 57 gamesꦯ♔ at a more superior level than the recorded human benchmark of performance within said games.
In the the field of AI, an agent i🐟s generally deemed intelligent if it performs of tasks. These 57 Atari games are used widely to test the intelligence of prospective AI agents because they pose a nice wide range of problem-solving, learning, and exploration tasks - the perfect playground for AI.
What's fascinating is that Agent57 started out performing awfully in the games, showing no signs of intelligence. But after only 120 minutes of playing Breakout, it starts playing like an exper�♛�t that matches the skill level of an adept human player.
After a further 120 minutes, however, Agent57 reaches superhuman performance levels. It manages to work out that the best way to play and beat the game is to dig a tunnel through the colored bricks and subsequently hit them💮 from b🐭ehind.
But what about the more challenging games? It's been noted that previous AI agents tend to fail at getting the hang of Atari's Montezuma’s Revenge, Pitfall, Solaris, and Skiing, because these require more longterm planning. Researchers have managed to enhance the performance of agents such as Agent57 in these games by infusing them with the very human capacity for . They make it all sound so easy.
Although 💖there is still work 🍬to be done, this is being called a .
Source: