--- title: "Training robots with crowdsourced feedback" id: "348" type: "post" slug: "training-robots-with-crowdsourced-feedback" published_at: "2023-11-28T09:58:06+00:00" modified_at: "2023-11-28T09:58:06+00:00" url: "https://louisecousins.co.uk/training-robots-with-crowdsourced-feedback/" markdown_url: "https://louisecousins.co.uk/training-robots-with-crowdsourced-feedback.md" excerpt: "Check out this cool new technique that’s making waves in the world of AI. So, you know how teaching AI agents can be a bit of a chore, especially with complex tasks like opening a kitchen cabinet? Well, researchers from..." taxonomy_category: - "Mechanical Engineering" taxonomy_post_tag: - "artificial intelligence" - "Artificial Intelligence (AI)" --- [Mechanical Engineering](https://louisecousins.co.uk/category/mechanical-engineering/) # Training robots with crowdsourced feedback [https://louisecousins.co.uk/author/lcousins/](https://louisecousins.co.uk/author/lcousins/) By [LCousins](https://louisecousins.co.uk/author/lcousins/) November 28, 2023 2 Min Read [3](https://louisecousins.co.uk/training-robots-with-crowdsourced-feedback/#comments) Check out this cool new technique that’s making waves in the world of AI. So, you know how teaching AI agents can be a bit of a chore, especially with complex tasks like opening a kitchen cabinet? Well, researchers from MIT, Harvard, and the University of Washington have come up with a game-changer! Usually, experts have to painstakingly design a reward system to motivate the AI to learn. It’s a bit of trial and error, and let’s face it, not the most efficient process. But these awesome folks have flipped the script. Instead of relying on expert-designed rewards, they’re tapping into the wisdom of the crowd. Picture this: you want to teach a robot a task, and instead of experts, regular folks from around the world can chime in with their feedback. Yeah, it might get a bit messy with errors, but guess what? This new approach makes the AI learn faster than ever before! Pulkit Agrawal, the brain behind this idea, says, “Our work proposes a way to scale robot learning by crowdsourcing the design of the reward function and by making it possible for nonexperts to provide useful feedback.” Fancy, right? They call it HuGE (Human Guided Exploration), and it’s all about letting the nonexpert users guide the AI’s exploration. It’s like they’re leaving little breadcrumbs to help the AI find its way to the goal. Marcel Torne, the lead author, explains, “Even if the human supervision is somewhat inaccurate and noisy, the agent is still able to explore, which helps it learn much better.” And get this – the AI doesn’t take the feedback too seriously. It uses it as a gentle nudge, exploring on its own and sending updates to the humans for a reality check. This method, tested on various tasks, proved to be faster and more effective than traditional approaches. Imagine a future where your robot can learn tasks at home without you having to babysit it. With HuGE, the possibilities are endless! The researchers are jazzed about refining HuGE to make the agent learn from other forms of communication, like language and physical interactions. They’re even thinking about applying it to teach multiple agents at once. Exciting times ahead! 🚀 **Story Source:** [Materials](https://news.mit.edu/2023/method-uses-crowdsourced-feedback-help-train-robots-1127) provided by [Massachusetts Institute of Technology](https://www.mit.edu/) . Original story written by Adam Zewe and can be found here: “New method uses crowdsourced feedback to help train robots.” ScienceDaily. ScienceDaily, 27 November 2023. [www.sciencedaily.com/releases/2023/11/231127132237.htm](http://www.sciencedaily.com/releases/2023/11/231127132237.htm) #### Tags: [artificial intelligence](https://louisecousins.co.uk/tag/artificial-intelligence/) [Artificial Intelligence (AI)](https://louisecousins.co.uk/tag/artificial-intelligence-ai/) [https://louisecousins.co.uk/author/lcousins/](https://louisecousins.co.uk/author/lcousins/) Author#### [LCousins](https://louisecousins.co.uk/author/lcousins/) [Follow Me](https://louisecousins.co.uk/author/lcousins/) ##### Other Articles [https://louisecousins.co.uk/what-is-going-on-at-openai/](https://louisecousins.co.uk/what-is-going-on-at-openai/) Previous ### [What iS going on at OpenAI?](https://louisecousins.co.uk/what-is-going-on-at-openai/) [https://louisecousins.co.uk/ai-enhanced-childrens-book/](https://louisecousins.co.uk/ai-enhanced-childrens-book/) Next ### [AI-Enhanced Childrens Book](https://louisecousins.co.uk/ai-enhanced-childrens-book/) ##### 3 Comments 1. Reading this felt like walking through a gallery of ideas, each one framed with care and presented with clarity. Your words have a way of making the abstract feel tangible, of bringing thoughts into sharp focus. [Reply](#comment-57) 2. Was just browsing louisecousins.co.uk and was impressed the layout. Nicely design and great user experience. Just had to drop a message, have a great day! [Reply](#comment-1095) 3. Was just browsing louisecousins.co.uk and was impressed the layout. Nicely design and great user experience. Just had to drop a message, have a great day! [Reply](#comment-1380) ### Leave a Reply [Cancel reply](/training-robots-with-crowdsourced-feedback/#respond) ## Latest Posts - [TPD003 The Difference Between Research and Knowledge Engineering](https://louisecousins.co.uk/003-the-difference-between-research-and-knowledge-engineering/) by LCousins July 8, 2026 - [TPD002 The day I realised my onboarding strategy had reached its limits.](https://louisecousins.co.uk/the-day-my-repository-became-too-big/) by LCousins July 6, 2026 - [TPD001 The AI I Had to Fire](https://louisecousins.co.uk/the-ai-i-had-to-fire/) by LCousins July 5, 2026 - [What Neurodiversity Taught Me About User Experience](https://louisecousins.co.uk/what-neurodiversity-taught-me-about-user-experience/) by LCousins June 9, 2026 - [Website Best Practices for 2026: Designing for Humans, AI, and an Increasingly Complex Digital World](https://louisecousins.co.uk/website-best-practices-2026/) by LCousins March 7, 2026 - [TPD000 The Beginning: Why I Started Learning AI the Long Way Round](https://louisecousins.co.uk/tpd000-the-beginning-why-i-started-learning-ai-the-long-way-round/) by LCousins February 22, 2026 - [When Less Website Traffic Doesn’t Always Spell Less Impact](https://louisecousins.co.uk/when-less-website-traffic-doesnt-always-spell-less-impact/) by LCousins November 21, 2025 - [Honouring the Past, Embracing the Present](https://louisecousins.co.uk/honouring-the-past-embracing-the-present/) by LCousins November 6, 2025 - [Misogyny and Sexual Harassment in the Workplace: The Harm of Covert Comments and Why Laughing It Off Is Not Consent](https://louisecousins.co.uk/misogyny-and-sexual-harassment-in-the-workplace-the-harm-of-covert-comments-and-why-laughing-it-off-is-not-consent/) by LCousins November 5, 2025 - [Empowering Women in Technology: A Call for Equity, Not Dominance – Part 1](https://louisecousins.co.uk/empowering-women-in-technology-a-call-for-equity-not-dominance-part-1/) by LCousins September 12, 2025 - [How Large Language Models Are Redefining the Future of SEO](https://louisecousins.co.uk/how-large-language-models-are-redefining-the-future-of-seo/) by LCousins September 4, 2025 - [The European Accessibility Act and Why Accessibility Matters Beyond Compliance](https://louisecousins.co.uk/the-european-accessibility-act-and-why-accessibility-matters-beyond-compliance/) by LCousins July 31, 2025 - [Website Best Practices for 2025](https://louisecousins.co.uk/website-best-practices-for-2025/) by LCousins June 2, 2025 - [Adventures in Dating: A Single Mum’s Journey Through Love in Her 40s](https://louisecousins.co.uk/adventures-in-dating-a-single-mums-journey-through-love-in-her-40s/) by LCousins May 19, 2025 - [Building Resilience: Living a Life in the Sunlight](https://louisecousins.co.uk/building-resilience-living-a-life-in-the-sunlight/) by LCousins May 11, 2025