The rapid pace of artificial intelligence (AI) has raised fears about whether robots could act unethically or soon choose to harm humans. Some are calling for bans on robotics research; others are calling for more research to understand how AI might be constrained. But how can robots learn ethical behavior if there is no “user manual” for being human?
Researchers Mark Riedl and Brent Harrison from the School of Interactive Computing at the Georgia Institute of Technology believe the answer lies in “Quixote” – to be unveiled at the AAAI-16 Conference in Phoenix, Ariz. (Feb. 12 – 17). Quixote 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,” says 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 crowdsourcing 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 randomly or like the antagonist.
Learn more: Using Stories to Teach Human Values to Artificial Agents
The Latest on: Using Stories to Teach Human Values to Artificial Agents
- Study shows AI conversational agents can help reduce interethnic prejudice during online interactionson May 10, 2024 at 10:37 am
Prejudice and fear have always been at the core of intergroup hostilities. While intergroup interaction is a prerequisite for initiating peace and stability at the junction of clashing interests, ...
- The Learning Networkon May 9, 2024 at 4:38 am
By The Learning Network Cheetahs can reach speeds of 58 m.p.h. or more. Bats use echolocation to fly in the dark. What do you find extraordinary about animals? By Michael Gonchar ...
- Artificial Intelligenceon May 8, 2024 at 11:36 pm
By Kevin Roose The system, AlphaFold3, could accelerate efforts to understand the human body and fight ... Airlines are using artificial intelligence to save fuel, keep customers informed and ...
- 6 values to teach your child by age 10on May 7, 2024 at 4:10 am
Today’s topic: 6 values to teach your child by age 10. A lot goes into raising kids beyond just providing the essentials of love, food, and shelter. Parents want their children to grow up and be ...
- Using Artificial Intelligence To Think Outside The Boxon May 3, 2024 at 3:05 pm
The enablement comes in the form of “rapidly analyzing the innovation pipeline to discover windows of opportunities," McKnight continues. "Algorithms can collect and connect relevant data on ...
- Artificial intelligence not possible without wealth of human knowledgeon May 2, 2024 at 10:30 pm
There is no artificial intelligence without the vast trove of human knowledge ... on such a thing or even to measure the collective value of such an incredible library. It definitely should ...
- Artificial Intelligence not possible without wealth of human knowledge | Editorialon May 2, 2024 at 7:50 am
There is no artificial ... collective value of such an incredible library. It definitely should not be free. But that’s the assumption made by OpenAI when it claims that its use of all this ...
- Editorial: Artificial Intelligence not possible without wealth of human knowledgeon May 2, 2024 at 7:32 am
There is no artificial ... collective value of such an incredible library. It definitely should not be free. But that’s the assumption made by OpenAI when it claims that its use of all this ...
- Using human intelligence to mitigate artificial intelligence riskson April 30, 2024 at 5:00 pm
Data loss prevention tools present employees with pop-up messages of the risk level of the app they’re using Share It is no secret that artificial intelligence is transforming the world of work.
- School principal was framed using AI-generated racist rant, police say. A co-worker is now charged.on April 25, 2024 at 6:20 am
BALTIMORE -- A former high school athletic director was arrested Thursday morning after allegedly using artificial intelligence to impersonate the school principal in a recording that included ...
via Bing News