Robots Teach Each Other How To Play Pac-Man

Pac-Man, the game since generations has been heavily downloaded, learned and played by people almost of all near generations. Children in the year of 1980 used to spend their time playing Namco’s Pac – Man PC game. However, the craze has still not ended. Those same children are even found to play Pac – Man in this time as well. But the most astonishing point about Pac Man is that, surprisingly even Robots are learning to play Pac – Man. Computers are being programmed in a way that they are making each other learn about the tactics of playing Pac – Man. The game required a manual user who was supposed to roam in the maze, navigating from here and there in such of pellets and a way to reach the final destination. But by getting followed by four different colored enemies, the user had to give in a lot of speed, mind and strategy.

Researchers and programmers have successfully developed a method that enables the computer to teach Pac – Man simultaneously to other computers. The teaching process undertakes the same way as it occurs between actual teacher and student. Matthew Taylor, the head of the team at Washington

State University’s Allred Distinguished Professor in Artificial Intelligence uses virtual robots that enable the process to undertake a simulation activity of teacher and student. The student robots took quite some time in learning Pac – Man. It was also essential to learn about StarCraft as well. But, they succeeded in surpassing their abilities ahead of the teacher. It is very challenging to teach and make a robot learn about games. Experts from Artificial Intelligence said, “If robots can learn to play games then they can even undertake other tasked like washing cars, household chores, office work, etc…

Professor Taylor said, “As robots become more common, we want them to be able to learn quickly and any time one robot learns something we want to make sure that it can teach that information to another robot, because we don’t want this information to be lost.” He also added, “As anyone with teenagers knows, the trick is in knowing when the robot should give advice. If it gives no advice, the robot is not teaching. But if it always gives advice, the student gets annoyed and doesn’t learn to outperform the teacher.”

Robots are being predicted to be smarter and efficient than humans in the years to come. Within next 15 – 20 years, the time is expected to change drastically. Ray Kurzwell, the expert artificial intelligence professional from the company stated that computers or robots would be efficient enough to undertake every task undertaken by humans. He said, “My project is ultimately to base search on really understanding what the language means. When you write an article, you're not creating an interesting collection of words. You have something to say and Google is devoted to intelligently organizing and processing the world's information. We want [computers] to read everything on the web and every page of every book, and then be able to engage in intelligent dialogue with the user to be able to answer their questions.”