October 25, 2018 04:06 pm
Original Link: http://rss.slashdot.org/~r/Slashdot/slashdot/~3/d3UlKo7MUsk/ibm-researchers-teach-pac-man-to-do-no-harm
IBM Researchers Teach Pac-Man To Do No Harm
harrymcc writes: The better AI gets at teaching itself to perform tasks in ways beyond the skills of mere humans, the more likely it is that it may unwittingly behave in ways a human would consider unethical. To explore ways to prevent this from happening, IBM researchers taught AI to play Pac-Man without ever gobbling up the ghosts. And it did so without ever explicitly telling the software that this was the goal. Over at Fast Company, I wrote about this project and what IBM learned from conducting it. The researchers built a piece of software that could balance the AI's ratio of self-devised, aggressive game play to human-influenced ghost avoidance, and tried different settings to see how they affected its overall approach to the game. By doing so, they found a tipping point -- the setting at which Pac-Man went from seriously chowing down on ghosts to largely avoiding them.Read more of this story at Slashdot.
Original Link: http://rss.slashdot.org/~r/Slashdot/slashdot/~3/d3UlKo7MUsk/ibm-researchers-teach-pac-man-to-do-no-harm
Share this article:
Tweet
View Full Article
Slashdot
Slashdot was originally created in September of 1997 by Rob "CmdrTaco" Malda. Today it is owned by Geeknet, Inc..More About this Source Visit Slashdot