Saturday, August 30, 2025
Science
No Result
View All Result
  • Login
  • HOME
  • SCIENCE NEWS
  • CONTACT US
  • HOME
  • SCIENCE NEWS
  • CONTACT US
No Result
View All Result
Scienmag
No Result
View All Result
Home Science News Mathematics

To build a better AI helper, start by modeling the irrational behavior of humans

April 22, 2024
in Mathematics
Reading Time: 4 mins read
0
To build a better AI helper, start by modeling the irrational behavior of humans
66
SHARES
599
VIEWS
Share on FacebookShare on Twitter
ADVERTISEMENT

CAMBRIDGE, MA – To build AI systems that can collaborate effectively with humans, it helps to have a good model of human behavior to start with. But humans tend to behave suboptimally when making decisions.

CAMBRIDGE, MA – To build AI systems that can collaborate effectively with humans, it helps to have a good model of human behavior to start with. But humans tend to behave suboptimally when making decisions.

This irrationality, which is especially difficult to model, often boils down to computational constraints. A human can’t spend decades thinking about the ideal solution to a single problem.

Researchers at MIT and the University of Washington developed a way to model the behavior of an agent, whether human or machine, that accounts for the unknown computational constraints that may hamper the agent’s problem-solving abilities.

Their model can automatically infer an agent’s computational constraints by seeing just a few traces of their previous actions. The result, an agent’s so-called “inference budget,” can be used to predict that agent’s future behavior.

In a new paper, the researchers demonstrate how their method can be used to infer someone’s navigation goals from prior routes and to predict players’ subsequent moves in chess matches. Their technique matches or outperforms another popular method for modeling this type of decision-making.

Ultimately, this work could help scientists teach AI systems how humans behave, which could enable these systems to respond better to their human collaborators. Being able to understand a human’s behavior, and then to infer their goals from that behavior, could make an AI assistant much more useful, says Athul Paul Jacob, an electrical engineering and computer science (EECS) graduate student and lead author of a paper on this technique.

“If we know that a human is about to make a mistake, having seen how they have behaved before, the AI agent could step in and offer a better way to do it. Or the agent could adapt to the weaknesses that its human collaborators have. Being able to model human behavior is an important step toward building an AI agent that can actually help that human,” he says.

Jacob wrote the paper with Abhishek Gupta, assistant professor at the University of Washington, and senior author Jacob Andreas, associate professor in EECS and a member of the Computer Science and Artificial Intelligence Laboratory (CSAIL). The research will be presented at the International Conference on Learning Representations.

 

Modeling behavior

Researchers have been building computational models of human behavior for decades. Many prior approaches try to account for suboptimal decision-making by adding noise to the model. Instead of the agent always choosing the correct option, the model might have that agent make the correct choice 95 percent of the time.

However, these methods can fail to capture the fact that humans do not always behave suboptimally in the same way.

Others at MIT have also studied more effective ways to plan and infer goals in the face of suboptimal decision-making.

To build their model, Jacob and his collaborators drew inspiration from prior studies of chess players. They noticed that players took less time to think before acting when making simple moves and that stronger players tended to spend more time planning than weaker ones in challenging matches.

“At the end of the day, we saw that the depth of the planning, or how long someone thinks about the problem, is a really good proxy of how humans behave,” Jacob says.

They built a framework that could infer an agent’s depth of planning from prior actions and use that information to model the agent’s decision-making process.

The first step in their method involves running an algorithm for a set amount of time to solve the problem being studied. For instance, if they are studying a chess match, they might let the chess-playing algorithm run for a certain number of steps. At the end, the researchers can see the decisions the algorithm made at each step.

Their model compares these decisions to the behaviors of an agent solving the same problem. It will align the agent’s decisions with the algorithm’s decisions and identify the step where the agent stopped planning.

From this, the model can determine the agent’s inference budget, or how long that agent will plan for this problem. It can use the inference budget to predict how that agent would react when solving a similar problem.

 

An interpretable solution

This method can be very efficient because the researchers can access the full set of decisions made by the problem-solving algorithm without doing any extra work. This framework could also be applied to any problem that can be solved with a particular class of algorithms.

“For me, the most striking thing was the fact that this inference budget is very interpretable. It is saying tougher problems require more planning or being a strong player means planning for longer. When we first set out to do this, we didn’t think that our algorithm would be able to pick up on those behaviors naturally,” Jacob says.

The researchers tested their approach in three different modeling tasks: inferring navigation goals from previous routes, guessing someone’s communicative intent from their verbal cues, and predicting subsequent moves in human-human chess matches.

Their method either matched or outperformed a popular alternative in each experiment. Moreover, the researchers saw that their model of human behavior matched up well with measures of player skill (in chess matches) and task difficulty.

Moving forward, the researchers want to use this approach to model the planning process in other domains, such as reinforcement learning (a trial-and-error method commonly used in robotics). In the long run, they intend to keep building on this work toward the larger goal of developing more effective AI collaborators.

###

This work was supported, in part, by the MIT Schwarzman College of Computing Artificial Intelligence for Augmentation and Productivity program and the National Science Foundation.



DOI

10.48550/arXiv.2312.04030

Share26Tweet17
Previous Post

In the United States, the election of progressive prosecutors led to higher relative rates of property and overall crime, but not to higher relative rates of violent crime

Next Post

European Court of Human Rights is “backsliding” on legal protections for asylum seekers, study says

Related Posts

blank
Mathematics

Applications for the 2026 Hertz Fellowship Are Now Open

August 29, 2025
blank
Mathematics

Quantum Twist Breathes New Life into 250-Year-Old Probability Theorem

August 29, 2025
blank
Mathematics

Mount Sinai Scientists Harness AI and Laboratory Tests to Forecast Genetic Disease Risk

August 28, 2025
blank
Mathematics

Quantum Breakthrough Fueled by MRI Technology and 2D Materials

August 28, 2025
blank
Mathematics

Illinois Study Explores New Ways to Relieve Gastrointestinal Symptoms in Cancer Patients

August 28, 2025
blank
Mathematics

Wax-Assisted Exfoliation and Dual-Surface AlOx Encapsulation Dramatically Boost Topological Phases in MnBi2Te4

August 28, 2025
Next Post
European Court of Human Rights is “backsliding” on legal protections for asylum seekers, study says

European Court of Human Rights is “backsliding” on legal protections for asylum seekers, study says

  • Mothers who receive childcare support from maternal grandparents show more parental warmth, finds NTU Singapore study

    Mothers who receive childcare support from maternal grandparents show more parental warmth, finds NTU Singapore study

    27542 shares
    Share 11014 Tweet 6884
  • University of Seville Breaks 120-Year-Old Mystery, Revises a Key Einstein Concept

    955 shares
    Share 382 Tweet 239
  • Bee body mass, pathogens and local climate influence heat tolerance

    642 shares
    Share 257 Tweet 161
  • Researchers record first-ever images and data of a shark experiencing a boat strike

    509 shares
    Share 204 Tweet 127
  • Warm seawater speeding up melting of ‘Doomsday Glacier,’ scientists warn

    313 shares
    Share 125 Tweet 78
Science

Embark on a thrilling journey of discovery with Scienmag.com—your ultimate source for cutting-edge breakthroughs. Immerse yourself in a world where curiosity knows no limits and tomorrow’s possibilities become today’s reality!

RECENT NEWS

  • Exploring Sex Differences in Health and Disease
  • Treadmill Training Decreases Astrocyte Reactivity in SCI Rats
  • Branched-Chain Amino Acids Fuel Tumor Growth
  • Daily vs. Alternate-Day Iron: Which Works Better?

Categories

  • Agriculture
  • Anthropology
  • Archaeology
  • Athmospheric
  • Biology
  • Blog
  • Bussines
  • Cancer
  • Chemistry
  • Climate
  • Earth Science
  • Marine
  • Mathematics
  • Medicine
  • Pediatry
  • Policy
  • Psychology & Psychiatry
  • Science Education
  • Social Science
  • Space
  • Technology and Engineering

Subscribe to Blog via Email

Enter your email address to subscribe to this blog and receive notifications of new posts by email.

Join 5,182 other subscribers

© 2025 Scienmag - Science Magazine

Welcome Back!

Login to your account below

Forgotten Password?

Retrieve your password

Please enter your username or email address to reset your password.

Log In
No Result
View All Result
  • HOME
  • SCIENCE NEWS
  • CONTACT US

© 2025 Scienmag - Science Magazine

Discover more from Science

Subscribe now to keep reading and get access to the full archive.

Continue reading