Why did the frog cross the road? Well, a new artificial intelligent (AI) agent that can play the classic arcade game Frogger not only can tell you why it crossed the road, but it can justify its every move in everyday language.
Developed by Georgia Tech, in collaboration with Cornell and the University of Kentucky, the work enables an AI agent to provide a rationale for a mistake or errant behavior, and to explain it in a way that is easy for non-experts to understand.
This, the researchers say, may help robots and other types of AI agents seem more relatable and trustworthy to humans. They also say their findings are an important step toward a more transparent, human-centered AI design that understands people’s preferences and prioritizes people’s needs.
“If the power of AI is to be democratized, it needs to be accessible to anyone regardless of their technical abilities,” said Upol Ehsan, Ph.D. student in the School of Interactive Computing at Georgia Tech and lead researcher.
“As AI pervades all aspects of our lives, there is a distinct need for human-centered AI design that makes black-boxed AI systems explainable to everyday users. Our work takes a formative step toward understanding the role of language-based explanations and how humans perceive them.”
The study was supported by the Office of Naval Research (ONR).
Researchers developed a participant study to determine if their AI agent could offer rationales that mimicked human responses. Spectators watched the AI agent play the videogame Frogger and then ranked three on-screen rationales in order of how well each described the AI’s game move.
Of the three anonymized justifications for each move – a human-generated response, the AI-agent response, and a randomly generated response – the participants preferred the human-generated rationales first, but the AI-generated responses were a close second.
Frogger offered the researchers the chance to train an AI in a “sequential decision-making environment,” which is a significant research challenge because decisions that the agent has already made influence future decisions. Therefore, explaining the chain of reasoning to experts is difficult, and even more so when communicating with non-experts, according to researchers.
In case the study participants weren’t familiar, the game’s goal of getting the frog safely home without being hit by moving vehicles or drowned in the river was explained to them. The simple game mechanics of moving up, down, left or right, allowed the participants to see what the AI was doing, and to reasonably evaluate if the rationales on the screen clearly justified the move.
The participants judged the rationales based on:
- Confidence – the person is confident in the AI to perform its task
- Human-likeness – looks like it was made by a human
- Adequate justification – adequately justifies the action taken
- Understandability – helps the person understand the AI’s behavior
AI-generated rationales that were ranked higher by participants were those that showed recognition of environmental conditions and adaptability, as well as those that communicated awareness of upcoming dangers and planned for them. Redundant information that just stated the obvious or misrepresented the environment were found to have a negative impact.
“This project is more about understanding human perceptions and preferences of these AI systems than it is about building new technologies,” said Ehsan. “At the heart of explainability is sensemaking. We are trying to understand that human factor.”
A second related study validated the researchers’ decision to design their AI agent to be able to offer one of two distinct types of rationales:
- Concise, “focused” rationales or
- Holistic, “complete picture” rationales
In this second study, participants were only offered AI-generated rationales after watching the AI play Frogger. They were asked to select the answer that they preferred in a scenario where an AI made a mistake or behaved unexpectedly. They did not know the rationales were grouped into the two categories.
By a 3-to-1 margin, participants favored answers that were classified in the “complete picture” category. Responses showed that people appreciated the AI thinking about future steps rather than just what was in the moment, which might make them more prone to making another mistake. People also wanted to know more so that they might directly help the AI fix the errant behavior.
“The situated understanding of the perceptions and preferences of people working with AI machines give us a powerful set of actionable insights that can help us design better human-centered, rationale-generating, autonomous agents,” said Mark Riedl, professor of Interactive Computing and lead faculty member on the project.
A possible future direction for the research will apply the findings to autonomous agents of various types, such as companion agents, and how they might respond based on the task at hand. Researchers will also look at how agents might respond in different scenarios, such as during an emergency response or when aiding teachers in the classroom.
The Latest on: AI agents
via Google News
The Latest on: AI agents
- TD Ameritrade Beefs Up Personalization With AIon November 18, 2019 at 2:19 pm
... on an AI engine called “voice of the customer analytics,” which builds on AI-based text and voice chatbots the company launched in 2017. The algorithm is trained on anonymized email, voice and ...
- MIT’s AI scores driver egotism to make autonomous vehicles more assertiveon November 18, 2019 at 12:00 pm
Over time and in this way, the AI came to understand when it’s appropriate to exhibit different driving ... but they’re planning to apply its model to pedestrians, bicycles, and other agents in ...
- GE Research, Siena College working together on the next innovation in AIon November 18, 2019 at 10:43 am
Peter Tu, chief scientist for AI at GE Research, explained the AI agent is being designed to learn like a child learns when growing up. The research is focused on the development of AI that can ...
- Predictions 2020: Artificial Intelligence (AI) and Customer Serviceon November 18, 2019 at 8:26 am
Here are some of the predictions from our full report: Improvements in AI will cause contact centers to rethink their outsourcing strategy. As automation handles the easy tasks, agents are left to ...
- The Risks of Using AI to Interpret Human Emotionson November 18, 2019 at 8:15 am
Ironically, the agents themselves may not even possess these biases, but clouded by the misconception that the algorithms are highly accurate, they may follow their advice blindly. In this way, biases ...
- Forecasting The Impact Of AI On The Apartment Leasing Processon November 18, 2019 at 5:02 am
AI has the potential to flip that reality on its head — especially for the leasing process. Artificial intelligence is starting to become and will continue to be a true business partner to property ...
- Google makes Contact Center AI generally availableon November 14, 2019 at 10:16 am
Read More Google Cloud on Thursday announced the general availability of Contact Center AI. The contact center software enables businesses to deploy virtual agents for basic customer interactions, and ...
- AI to determine when to intervene with your drivingon November 13, 2019 at 6:42 am
Can your AI agent judge when to talk to you while you are driving? According to a research team, their in-vehicle conservation service technology will judge when it is appropriate to contact you to ...
- Google’s AI Customer Service Agent CallJoy Gets Smarteron November 12, 2019 at 5:04 am
Earlier this year, Google unveiled CallJoy, a virtual customer service agent for small businesses which complements its Duplex calling system. The functions were somewhat limited at the time, but now, ...
- Google updates CallJoy phone agent with customizable AI featureson November 12, 2019 at 5:00 am
Google said the more information a small business owner gives to the agent, the smarter and more responsive CallJoy becomes. Developed as part of Area 120, CallJoy rolls existing Google technologies - ...
via Bing News