Robots Learn Human Ethics by Reading Stories
The rapid advance of artificial intelligence (AI) is raising concerns about robots acting unethically or choosing to harm humans. But how can robots learn ethical behavior if there is no “user manual” for being human?
Researchers Mark Riedl and Brent Harrison from Georgia Tech’s School of Interactive Computing believe the answer lies in “Quixote,” a technique that teaches “value alignment” to robots by training them to read stories, learn acceptable sequences of events, and understand successful ways to behave in human societies.
“The collected stories of different cultures teach children how to behave in socially acceptable ways with examples of proper and improper behavior in fables, novels, and other literature,” said Riedl, associate professor and director of the Entertainment Intelligence Lab. “We believe story comprehension in robots can eliminate psychotic-appearing behavior and reinforce choices that won’t harm humans and still achieve the intended purpose.”
Quixote is a technique for aligning an AI’s goals with human values by placing rewards on socially appropriate behavior. It builds upon Riedl’s prior research — the Scheherazade system — which demonstrated how artificial intelligence can gather a correct sequence of actions by crowd-sourcing story plots from the Internet.
Scheherazade learns what is a normal or “correct” plot graph. It then passes that data structure along to Quixote, which converts it into a “reward signal” that reinforces certain behaviors and punishes other behaviors during trial-and-error learning. In essence, Quixote learns that it will be rewarded whenever it acts like the protagonist in a story instead of behaving randomly or like the antagonist.
Presented at the AAAI-16 Conference, the research was supported by the Defense Advanced Research Projects Agency (DARPA) and the Office of Naval Research (ONR). — Tara La Bouff
