* . *
  • About
  • Advertise
  • Privacy & Policy
  • Contact
Saturday, August 30, 2025
Earth-News
  • Home
  • Business
  • Entertainment
    Sabrina Carpenter’s pearl-clutching magic? Humor – CNN

    Sabrina Carpenter’s pearl-clutching magic? Humor – CNN

    South Park Is In Trouble And Needs To Change Course, Fast – yahoo.com

    South Park Faces Major Challenges and Must Adapt Fast to Survive

    ‘Netflix House’ entertainment complexes are coming. Here’s when they open – Los Angeles Times

    Exciting News: Netflix’s House Entertainment Complexes Are Opening Soon!

    ‘Big Brother’s’ Rylie Jeffries Finally Speaks Out on Katherine Woodman Controversy – El Paso Inc.

    Big Brother’s Rylie Jeffries Finally Speaks Out on Katherine Woodman Controversy

    ‘SNL’ Parts Ways With Emil Wakim Amid Rumored Season 51 Cast Shakeup – yahoo.com

    SNL Shakes Up Season 51 Cast with Emil Wakim’s Surprising Exit

    Do you have a favorable or an unfavorable opinion of Taylor Swift? – YouGov

    Do You Love Taylor Swift or Not? Share Your Thoughts!

  • General
  • Health
  • News

    Cracking the Code: Why China’s Economic Challenges Aren’t Shaking Markets, Unlike America’s” – Bloomberg

    Trump’s Narrow Window to Spread the Truth About Harris

    Trump’s Narrow Window to Spread the Truth About Harris

    Israel-Gaza war live updates: Hamas leader Ismail Haniyeh assassinated in Iran, group says

    Israel-Gaza war live updates: Hamas leader Ismail Haniyeh assassinated in Iran, group says

    PAP Boss to Niger Delta Youths, Stay Away from the Protest

    PAP Boss to Niger Delta Youths, Stay Away from the Protest

    Court Restricts Protests In Lagos To Freedom, Peace Park

    Court Restricts Protests In Lagos To Freedom, Peace Park

    Fans React to Jazz Jennings’ Inspiring Weight Loss Journey

    Fans React to Jazz Jennings’ Inspiring Weight Loss Journey

    Trending Tags

    • Trump Inauguration
    • United Stated
    • White House
    • Market Stories
    • Election Results
  • Science
  • Sports
  • Technology
    Propelling solar technology into a perovskite future – CORDIS

    Propelling solar technology into a perovskite future – CORDIS

    13 Top Technology Trends (2025) – Exploding Topics

    13 Game-Changing Technology Trends to Watch in 2025

    Japan’s legacy LCD and chip technology find new home in India – Nikkei Asia

    How Japan’s Breakthrough LCD and Chip Technologies Are Driving Innovation in India

    ITSWC 2025: Thursday sessions guide – Traffic Technology Today

    Your Ultimate Guide to Thursday Sessions at ITSWC 2025

    MC Machinery Technology Summit Showcases Manufacturing Innovations – Modern Machine Shop

    MC Machinery Technology Summit Unveils Cutting-Edge Manufacturing Innovations

    US-ROK Technology Cooperation Faces Rising Tensions – The National Interest

    Rising Tensions Put US-South Korea Technology Partnership to the Test

    Trending Tags

    • Nintendo Switch
    • CES 2017
    • Playstation 4 Pro
    • Mark Zuckerberg
No Result
View All Result
  • Home
  • Business
  • Entertainment
    Sabrina Carpenter’s pearl-clutching magic? Humor – CNN

    Sabrina Carpenter’s pearl-clutching magic? Humor – CNN

    South Park Is In Trouble And Needs To Change Course, Fast – yahoo.com

    South Park Faces Major Challenges and Must Adapt Fast to Survive

    ‘Netflix House’ entertainment complexes are coming. Here’s when they open – Los Angeles Times

    Exciting News: Netflix’s House Entertainment Complexes Are Opening Soon!

    ‘Big Brother’s’ Rylie Jeffries Finally Speaks Out on Katherine Woodman Controversy – El Paso Inc.

    Big Brother’s Rylie Jeffries Finally Speaks Out on Katherine Woodman Controversy

    ‘SNL’ Parts Ways With Emil Wakim Amid Rumored Season 51 Cast Shakeup – yahoo.com

    SNL Shakes Up Season 51 Cast with Emil Wakim’s Surprising Exit

    Do you have a favorable or an unfavorable opinion of Taylor Swift? – YouGov

    Do You Love Taylor Swift or Not? Share Your Thoughts!

  • General
  • Health
  • News

    Cracking the Code: Why China’s Economic Challenges Aren’t Shaking Markets, Unlike America’s” – Bloomberg

    Trump’s Narrow Window to Spread the Truth About Harris

    Trump’s Narrow Window to Spread the Truth About Harris

    Israel-Gaza war live updates: Hamas leader Ismail Haniyeh assassinated in Iran, group says

    Israel-Gaza war live updates: Hamas leader Ismail Haniyeh assassinated in Iran, group says

    PAP Boss to Niger Delta Youths, Stay Away from the Protest

    PAP Boss to Niger Delta Youths, Stay Away from the Protest

    Court Restricts Protests In Lagos To Freedom, Peace Park

    Court Restricts Protests In Lagos To Freedom, Peace Park

    Fans React to Jazz Jennings’ Inspiring Weight Loss Journey

    Fans React to Jazz Jennings’ Inspiring Weight Loss Journey

    Trending Tags

    • Trump Inauguration
    • United Stated
    • White House
    • Market Stories
    • Election Results
  • Science
  • Sports
  • Technology
    Propelling solar technology into a perovskite future – CORDIS

    Propelling solar technology into a perovskite future – CORDIS

    13 Top Technology Trends (2025) – Exploding Topics

    13 Game-Changing Technology Trends to Watch in 2025

    Japan’s legacy LCD and chip technology find new home in India – Nikkei Asia

    How Japan’s Breakthrough LCD and Chip Technologies Are Driving Innovation in India

    ITSWC 2025: Thursday sessions guide – Traffic Technology Today

    Your Ultimate Guide to Thursday Sessions at ITSWC 2025

    MC Machinery Technology Summit Showcases Manufacturing Innovations – Modern Machine Shop

    MC Machinery Technology Summit Unveils Cutting-Edge Manufacturing Innovations

    US-ROK Technology Cooperation Faces Rising Tensions – The National Interest

    Rising Tensions Put US-South Korea Technology Partnership to the Test

    Trending Tags

    • Nintendo Switch
    • CES 2017
    • Playstation 4 Pro
    • Mark Zuckerberg
No Result
View All Result
Earth-News
No Result
View All Result
Home Science

HuGE AI Breakthrough: Using Crowdsourced Feedback in Robot Training

November 27, 2023
in Science
HuGE AI Breakthrough: Using Crowdsourced Feedback in Robot Training
Share on FacebookShare on Twitter

Crowdsource AI Robot Training Concept

A novel reinforcement learning method, HuGE, developed by MIT, Harvard, and the University of Washington researchers, uses crowdsourced feedback to efficiently teach AI agents complex tasks, showing promising results in both simulations and real-world applications.

Human Guided Exploration (HuGE) enables AI agents to learn quickly with some help from humans, even if the humans make mistakes.

To teach an AI agent a new task, like how to open a kitchen cabinet, researchers often use reinforcement learning — a trial-and-error process where the agent is rewarded for taking actions that get it closer to the goal.

In many instances, a human expert must carefully design a reward function, which is an incentive mechanism that gives the agent motivation to explore. The human expert must iteratively update that reward function as the agent explores and tries different actions. This can be time-consuming, inefficient, and difficult to scale up, especially when the task is complex and involves many steps.

Innovations in Reinforcement Learning

Researchers from MIT, Harvard University, and the University of Washington have developed a new reinforcement learning approach that doesn’t rely on an expertly designed reward function. Instead, it leverages crowdsourced feedback, gathered from many nonexpert users, to guide the agent as it learns to reach its goal.

While some other methods also attempt to utilize nonexpert feedback, this new approach enables the AI agent to learn more quickly, despite the fact that data crowdsourced from users are often full of errors. These noisy data might cause other methods to fail.

In addition, this new approach allows feedback to be gathered asynchronously, so nonexpert users around the world can contribute to teaching the agent.

“HuGE”: A Novel Approach

“One of the most time-consuming and challenging parts in designing a robotic agent today is engineering the reward function. Today reward functions are designed by expert researchers — a paradigm that is not scalable if we want to teach our robots many different tasks. Our work proposes a way to scale robot learning by crowdsourcing the design of reward function and by making it possible for nonexperts to provide useful feedback,” says Pulkit Agrawal, an assistant professor in the MIT Department of Electrical Engineering and Computer Science (EECS) who leads the Improbable AI Lab in the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL).

In the future, this method could help a robot learn to perform specific tasks in a user’s home quickly, without the owner needing to show the robot physical examples of each task. The robot could explore on its own, with crowdsourced nonexpert feedback guiding its exploration.

“In our method, the reward function guides the agent to what it should explore, instead of telling it exactly what it should do to complete the task. So, even if the human supervision is somewhat inaccurate and noisy, the agent is still able to explore, which helps it learn much better,” explains lead author Marcel Torne ’23, a research assistant in the Improbable AI Lab.

Torne is joined on the paper by his MIT advisor, Agrawal; senior author Abhishek Gupta, assistant professor at the University of Washington; as well as others at the University of Washington and MIT. The research will be presented at the Conference on Neural Information Processing Systems next month.

Feedback Mechanism and Learning Process

One way to gather user feedback for reinforcement learning is to show a user two photos of states achieved by the agent, and then ask the user which state is closer to a goal. For instance, perhaps a robot’s goal is to open a kitchen cabinet. One image might show that the robot opened the cabinet, while the second might show that it opened the microwave. A user would pick the photo of the “better” state.

Some previous approaches try to use this crowdsourced, binary feedback to optimize a reward function that the agent would use to learn the task. However, because non-experts are likely to make mistakes, the reward function can become very noisy, so the agent might get stuck and never reach its goal.

“Basically, the agent would take the reward function too seriously. It would try to match the reward function perfectly. So, instead of directly optimizing over the reward function, we just use it to tell the robot which areas it should be exploring,” Torne says.

He and his collaborators decoupled the process into two separate parts, each directed by its own algorithm. They call their new reinforcement learning method HuGE (Human Guided Exploration).

On one side, a goal selector algorithm is continuously updated with crowdsourced human feedback. The feedback is not used as a reward function, but rather to guide the agent’s exploration. In a sense, the nonexpert users drop breadcrumbs that incrementally lead the agent toward its goal.

On the other side, the agent explores on its own, in a self-supervised manner guided by the goal selector. It collects images or videos of actions that it tries, which are then sent to humans and used to update the goal selector.

This narrows down the area for the agent to explore, leading it to more promising areas that are closer to its goal. But if there is no feedback, or if feedback takes a while to arrive, the agent will keep learning on its own, albeit in a slower manner. This enables feedback to be gathered infrequently and asynchronously.

“The exploration loop can keep going autonomously, because it is just going to explore and learn new things. And then when you get some better signal, it is going to explore in more concrete ways. You can just keep them turning at their own pace,” adds Torne.

And because the feedback is just gently guiding the agent’s behavior, it will eventually learn to complete the task even if users provide incorrect answers.

Faster Learning

The researchers tested this method on a number of simulated and real-world tasks. In simulation, they used HuGE to effectively learn tasks with long sequences of actions, such as stacking blocks in a particular order or navigating a large maze.

In real-world tests, they utilized HuGE to train robotic arms to draw the letter “U” and pick and place objects. For these tests, they crowdsourced data from 109 nonexpert users in 13 different countries spanning three continents.

HuGE Robot Training

In real-world tests, researchers utilized HuGE to train robotic arms to pick and place objects and to draw the letter “U.” They crowdsourced data from 109 nonexpert users in 13 different countries spanning three continents. Credit: Courtesy of the researchers

In real-world and simulated experiments, HuGE helped agents learn to achieve the goal faster than other methods.

The researchers also found that data crowdsourced from nonexperts yielded better performance than synthetic data, which were produced and labeled by the researchers. For nonexpert users, labeling 30 images or videos took fewer than two minutes.

“This makes it very promising in terms of being able to scale up this method,” Torne adds.

In a related paper, which the researchers presented at the recent Conference on Robot Learning, they enhanced HuGE so an AI agent can learn to perform the task, and then autonomously reset the environment to continue learning. For instance, if the agent learns to open a cabinet, the method also guides the agent to close the cabinet.

“Now we can have it learn completely autonomously without needing human resets,” he says.

The researchers also emphasize that, in this and other learning approaches, it is critical to ensure that AI agents are aligned with human values.

In the future, they want to continue refining HuGE so the agent can learn from other forms of communication, such as natural language and physical interactions with the robot. They are also interested in applying this method to teach multiple agents at once.

Reference: “Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback” by Marcel Torne, Max Balsells, Zihan Wang, Samedh Desai, Tao Chen, Pulkit Agrawal and Abhishek Gupta, 20 July 2023, Computer Science> Machine Learning.
arXiv:2307.11049

This research is funded, in part, by the MIT-IBM Watson AI Lab.

>>> Read full article>>>
Copyright for syndicated content belongs to the linked Source : SciTechDaily – https://scitechdaily.com/huge-ai-breakthrough-using-crowdsourced-feedback-in-robot-training/

Tags: Breakthroughscienceusing
Previous Post

Strange Chemistry: Webb Reveals “Teenage Galaxies” Are Unusually Hot, Glowing With Unexpected Elements

Next Post

New Research Indicates That Atherosclerosis – Thought To Be Irreversible – Can Be Reversed

FAU tells ‘story’ of Atlantic’s sargassum surge using 40 years of data – EurekAlert!

FAU Reveals the Untold Story Behind Four Decades of Atlantic Sargassum Surge

August 30, 2025
This Week in Science: Brain-Boosting Smells, The Brightest Flash Ever, And More! – ScienceAlert

This Week in Science: Brain-Boosting Scents, The Brightest Flash Ever, and Exciting Discoveries!

August 30, 2025
7 Speed Mike Stewart Science Bodyboard Launch Flex 7 Polypropylene (Polypro) Crescent Tail Morey Mach 7ss – The Michigan Review

Unleash Your Potential with the 7 Speed Mike Stewart Science Bodyboard Featuring Flex 7 Polypropylene and Crescent Tail

August 30, 2025
Cardiologists Struggle With Lifestyle Recommendations – Medscape

Cardiologists Struggle With Lifestyle Recommendations – Medscape

August 30, 2025
Propelling solar technology into a perovskite future – CORDIS

Propelling solar technology into a perovskite future – CORDIS

August 30, 2025
Brian Schottenheimer addresses Micah Parsons trade, says Cowboys can’t win Super Bowl ‘with just one person’ – CBS Sports

Brian Schottenheimer Explains Why the Cowboys Need More Than One Star to Win the Super Bowl

August 30, 2025

First Human Case of New World Screwworm in the US: What You Need to Know

August 30, 2025
Canadian Economy Contracts 0.4%; US Tariffs Drive Losses – Mexico Business News

Canadian Economy Contracts 0.4% Amid Rising US Tariff Pressures on Trade

August 30, 2025
Sabrina Carpenter’s pearl-clutching magic? Humor – CNN

Sabrina Carpenter’s pearl-clutching magic? Humor – CNN

August 30, 2025
The vaccine and public health debate at the center of CDC upheaval, explained – CNBC

The vaccine and public health debate at the center of CDC upheaval, explained – CNBC

August 30, 2025

Categories

Archives

August 2025
MTWTFSS
 123
45678910
11121314151617
18192021222324
25262728293031
« Jul    
Earth-News.info

The Earth News is an independent English-language daily published Website from all around the World News

Browse by Category

  • Business (20,132)
  • Ecology (798)
  • Economy (817)
  • Entertainment (21,696)
  • General (16,761)
  • Health (9,858)
  • Lifestyle (831)
  • News (22,149)
  • People (818)
  • Politics (824)
  • Science (16,027)
  • Sports (21,315)
  • Technology (15,797)
  • World (798)

Recent News

FAU tells ‘story’ of Atlantic’s sargassum surge using 40 years of data – EurekAlert!

FAU Reveals the Untold Story Behind Four Decades of Atlantic Sargassum Surge

August 30, 2025
This Week in Science: Brain-Boosting Smells, The Brightest Flash Ever, And More! – ScienceAlert

This Week in Science: Brain-Boosting Scents, The Brightest Flash Ever, and Exciting Discoveries!

August 30, 2025
  • About
  • Advertise
  • Privacy & Policy
  • Contact

© 2023 earth-news.info

No Result
View All Result

© 2023 earth-news.info

No Result
View All Result

© 2023 earth-news.info

Go to mobile version