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
- Google open-sources datasets for AI assistants with human-level understandingon September 6, 2019 at 2:10 pm
Both datasets are being shared by Google AI researchers to supply the training ... where one human plays the role of the agent and workers from temporary worker websites portray an average digital ...
- AI: The Somnium Files Physical Released Delayed in North Americaon September 6, 2019 at 5:28 am
In AI: The Somnium Files, it seems the mystery will begin when a woman’s body is found at a theme park. When Special Agent Date arrives at the crime scene, the initial clues lead him to an unlikely ...
- Bellevue insurance startup that uses artificial intelligence sold for $2.3 billionon September 5, 2019 at 6:12 pm
Agents can be matched with customers based on age ... “Insurance, as you may know, is not an easy thing to buy,” Agarwal said. “So how they use artificial intelligence and the human touch together to ...
- Accenture's head of artificial intelligence shares the 4-step plan every company should consider before investing in AIon September 5, 2019 at 6:26 am
Athina Kanioura says firms shouldn't pursue a tech upgrade as a solution for every problem. Instead, she urges them to think about an "AI narrative." ...
- Allen Institute’s Aristo AI system finally passes an eighth-grade science teston September 4, 2019 at 6:58 pm
The work builds on a series of language-interpreting, question-answering AI agents including AI2’s ELMo program and the BERT program developed at Google’s research facility in Seattle. Aristo takes ...
- Spending on AI systems set to surge and consultants are going to thriveon September 4, 2019 at 11:13 am
China and Japan will show the strongest spending growth over 5 years. Use cases vary, but the largest AI uses in 2019 revolve around automated customer service agents, threat intelligence and ...
- The question of AI for ServiceNow is a question of what workson September 4, 2019 at 10:55 am
"AI is by definition the ability to do the right thing," he says ... "Their users have to have a conversation with a virtual agent which would have to understand their lingo." Every single term can ...
- Autonomous Agents Market 2019 Current Industry Status and Growth Opportunities, Top Key Players, Target Audience And Forecast To 2026on September 3, 2019 at 5:57 pm
Market Drivers The Autonomous Agents Market report profiles the following companies, Oracle, IBM Corporation, SAP SE, Amazon Web Services, Inc., SAS Institute Inc., Infosys Limited, Nuance ...
- AI: When to Play It Safe and When It’s Risky Businesson September 3, 2019 at 3:05 pm
Intelligent Assistance (IA) – AI applications for your staff, not your customers – in the realm of customer experience refers to technology that augments support agents and streamlines workflow. Think ...
- GBT’s AI “Smart Agent”- Phase I Completed “The Agent” Officially Releasedon August 30, 2019 at 10:04 pm
SANTA MONICA, Calif., Aug. 30, 2019 (GLOBE NEWSWIRE) -- GBT Technologies Inc., (OTC PINK: GTCH) ("GBT”, or the “Company”), a company specializing in the development of Internet of Things ...
via Bing News