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
- Facebook makes big advances in AI reasoning and machine translationon October 16, 2019 at 10:55 am
AI reasoning models are trained using reinforcement learning, which is a programming method that trains algorithms using a system of reward and punishment. A reinforcement learning algorithm, or agent ...
- Do we trust artificial intelligence agents to mediate conflict? Not entirelyon October 16, 2019 at 7:34 am
We may listen to facts from Siri or Alexa, or directions from Google Maps or Waze, but would we let a virtual agent enabled by artificial intelligence help mediate conflict among team members? A new ...
- TUGU Insurance launches AI-enabled app for agents and policyholderson October 16, 2019 at 2:09 am
Indonesian insurance provider TUGU Insurance has launched the “tdrive” mobile app to deliver a seamless brand experience to its agents and customers. Developed by Singapore-based insurtech company ...
- eGain Reimagines Omnichannel Customer Engagement with Conversational Automation, Augmented Agents, and Full-Spectrum Analyticson October 15, 2019 at 6:13 pm
... www.egain.com/messaging-hub SOLVE eGain Sales Advisor™ makes all your sales agents as good as your best sales agent with best-practice process guidance. Easy to deploy and manage, it is built on ...
- OpenAI’s AI-powered robot learned how to solve a Rubik’s cube one-handedon October 15, 2019 at 10:00 am
But until recently, it’s been much easier to train an AI agent to do something virtually — playing a computer game, for example — than to train it to perform a real-world task. That’s because training ...
- Why We Need To Rethink Central Authority In The Age of AIon October 12, 2019 at 6:24 am
We live in an age of increasing centralization that pervades all aspects of our culture. In today’s world, centralization equates to control; centralization equates to power. Centralization gave rise ...
- Toyota LQ Has Something Called The 'Yui' Artificial Intelligence Agenton October 10, 2019 at 11:03 pm
It's visiting the Tokyo Motor Show from the year 2040, probably. Onboard Artificial Intelligence Agent "Yui" delivers personalized driving experience Toyota-developed SAE Level 4 equivalent automated ...
- AI Ethics Come Into Focus as Workplace Evolveson October 10, 2019 at 6:06 pm
or text generated by AI systems), companies can help build trust with stakeholders by being transparent about their AI use. For instance, rather than masquerade as humans, intelligent agents or ...
- Salesforce finds a new use for its Einstein AI: shark spottingon October 9, 2019 at 1:10 pm
Salesforce.com Inc. provides a suite of machine learning tools called Einstein designed to improve the productivity of salespeople, help desk agents and other knowledge workers. Now, the company is ...
- Researchers develop AI that can play Angry Birdson October 8, 2019 at 9:56 am
In a preprint paper published this week on Arxiv.org, researchers at Charles University in Prague detail an AI system — DQ-Birds — trained using Deep Q-learning, a technique pioneered by Alphabet’s ...
via Bing News