Friday, July 25, 2025
LBNN
  • Business
  • Markets
  • Politics
  • Crypto
  • Finance
  • Energy
  • Technology
  • Taxes
  • Creator Economy
  • Wealth Management
  • Documentaries
No Result
View All Result
LBNN

New framework mimics human lifelong learning

Simon Osuji by Simon Osuji
February 20, 2025
in Artificial Intelligence
0
New framework mimics human lifelong learning
0
SHARES
0
VIEWS
Share on FacebookShare on Twitter


A robotic reinforcement learning framework designed to mimic human lifelong learning
Concept illustration of robotic LRL process. a, Overview illustration of the general LRL process. Unlike the conventional multi-task approaches, where agents have simultaneous access to all tasks, an LRL agent can master tasks sequentially, one after another. Moreover, the agent should continually accumulate knowledge throughout the process. This concept emulates the human learning process. b, Our proposed framework under the lifelong learning concept. We instruct the deployed embodied agent to perform long-horizon tasks using language commands. The agent accomplishes these tasks through the combination and reapplication of acquired knowledge. Credit: Meng et al. (Nature Machine Intelligence, 2025).

Humans are known to accumulate knowledge over time, which in turn allows them to continuously improve their abilities and skills. This capability, known as lifelong learning, has so far proved difficult to replicate in artificial intelligence (AI) and robotics systems.

Related posts

Trump’s Anti-Bias AI Order Is Just More Bias

Trump’s Anti-Bias AI Order Is Just More Bias

July 25, 2025
Harvard’s ultra-thin chip could revolutionize quantum computing

Harvard’s ultra-thin chip could revolutionize quantum computing

July 25, 2025

A research team at Technical University of Munich and Nanjing University, led by Prof. Alois Knoll and Dr. Zhenshan Bing, has developed LEGION, a new reinforcement learning framework that could equip robotic systems with lifelong learning capabilities.

Their proposed framework, presented in a paper in Nature Machine Intelligence, could help to enhance the adaptability of robots, while also improving their performance in real-world settings.

“Our research originated from a project on robotic meta-reinforcement learning in 2021, where we initially explored Gaussian mixture models (GMM) as priors for task inference and knowledge clustering,” Yuan Meng, first author of the paper, told Tech Xplore.

“While this approach yielded promising results, we encountered a limitation—GMMs require a predefined number of clusters, making them unsuitable for lifelong learning scenarios where the number of tasks is inherently unknown and evolves asynchronously.

“To address this, we turned to Bayesian non-parametric models, specifically Dirichlet Process Mixture Models (DPMMs), which can dynamically adjust the number of clusters based on incoming task data.”

Leveraging a class of models known as DPMMs, the LEGION framework allows algorithms trained via reinforcement learning to continuously acquire, preserve and re-apply knowledge across a changing stream of tasks. The researchers hope that this new framework will help to enhance the learning abilities of AI agents, bringing them one step closer to the lifelong learning observed in humans.

“The LEGION framework is designed to mimic human lifelong learning by allowing a robot to continuously learn new tasks while preserving and reusing previously acquired knowledge,” explained Meng.

“Its key contribution is a non-parametric knowledge space based on a DPMM, which dynamically determines how knowledge is structured without requiring a predefined number of task clusters. This prevents catastrophic forgetting and allows flexible adaptation to new, unseen tasks.”






Demonstrating the real-world performance of the proposed LEGION framework in solving the long-horizon manipulation task: “clean the table.” Credit: Nature Machine Intelligence (2025). DOI: 10.1038/s42256-025-00983-2

The new framework introduced by Meng, Prof. Knoll, Dr. Bing and their colleagues integrates language embeddings that are encoded from a pre-trained large language model (LLM). This integration ultimately allows robots to process and understand a user’s instructions, interpreting these instructions independently from task demonstrations.

“Furthermore, our framework facilitates knowledge recombination, meaning a robot can solve long-horizon tasks—such as cleaning a table—by intelligently sequencing previously learned skills like pushing objects, opening drawers, or pressing buttons,” said Meng.

“Unlike conventional imitation learning, which relies on predefined execution sequences, LEGION allows for flexible skill combination in any required order, leading to greater generalization and flexibility in real-world robotic applications.”

The researchers evaluated their approach in a series of initial tests, applying it to a real robotic system. Their findings were very promising, as the LEGION framework allowed the robot to consistently accumulate knowledge from a continuous stream of tasks.

“We demonstrated that non-parametric Bayesian models, specifically DPMM, can serve as effective prior knowledge for robotic lifelong learning,” said Meng. “Unlike traditional multi-task learning, where all tasks are learned simultaneously, our framework can dynamically adapt to an unknown number task stream, preserving and recombining knowledge to improve performance over time.”

The recent work by Meng, Prof. Knoll, Dr. Bing and their colleagues could inform future efforts aimed at developing robots that can continuously acquire knowledge and refine their skills over time. The LEGION framework could be improved further and applied to a wide range of robots, including service robots and industrial robots.

“For example, a robot deployed in a home environment could learn household chores over time, refining its skills based on user feedback and adapting to new tasks as they arise,” said Meng. “Similarly, in industrial settings, robots could incrementally learn and adapt to changing production lines without requiring extensive reprogramming.”

In their next studies, the researchers plan to work on further enhancing the stability vs. plasticity trade-off in lifelong learning, as this would allow robots to reliably retain knowledge over time, while also adapting to new environments or tasks. To do this, they will integrate various computational techniques, including generative replay and continual backpropagation.

“Another key direction for future research will be cross-platform knowledge transfer, where a robot can transfer and adapt learned knowledge across different embodiments, such as humanoid robots, robotic arms, and mobile platforms,” added Meng.

“We also seek to expand LEGION’s capabilities beyond structured environments, allowing robots to handle unstructured, dynamic real-world settings with diverse object arrangements. Finally, we envision leveraging LLMs for real-time reward adaptation, enabling robots to refine their task objectives dynamically based on verbal or contextual feedback.”

More information:
Yuan Meng et al, Preserving and combining knowledge in robotic lifelong reinforcement learning, Nature Machine Intelligence (2025). DOI: 10.1038/s42256-025-00983-2.

© 2025 Science X Network

Citation:
Continuous skill acquisition in robots: New framework mimics human lifelong learning (2025, February 20)
retrieved 20 February 2025
from https://techxplore.com/news/2025-02-skill-acquisition-robots-framework-mimics.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.





Source link

Previous Post

South African pharmaceutical wholesaler UPD adds 42 electric vans to fleet

Next Post

Why sub-surface gas storage will be key to Scotland’s hydrogen ambitions

Next Post
Why sub-surface gas storage will be key to Scotland’s hydrogen ambitions

Why sub-surface gas storage will be key to Scotland's hydrogen ambitions

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

RECOMMENDED NEWS

Meet Sani Bello: Ex-military leader turned oil mogul

Meet Sani Bello: Ex-military leader turned oil mogul

3 months ago
How High Can ETH Surge In December 2024?

How High Can ETH Surge In December 2024?

8 months ago
France keeps its promise to even the score with Algeria as relations become ‘totally blocked’

France keeps its promise to even the score with Algeria as relations become ‘totally blocked’

2 months ago
Meet AgentZero, the AI that Writes Emails For You – IT News Africa

Meet AgentZero, the AI that Writes Emails For You – IT News Africa

2 years ago

POPULAR NEWS

  • Ghana to build three oil refineries, five petrochemical plants in energy sector overhaul

    Ghana to build three oil refineries, five petrochemical plants in energy sector overhaul

    0 shares
    Share 0 Tweet 0
  • When Will SHIB Reach $1? Here’s What ChatGPT Says

    0 shares
    Share 0 Tweet 0
  • The world’s top 10 most valuable car brands in 2025

    0 shares
    Share 0 Tweet 0
  • Top 10 African countries with the highest GDP per capita in 2025

    0 shares
    Share 0 Tweet 0
  • Tanzania’s natural gas sector goes global with Dubai deal

    0 shares
    Share 0 Tweet 0
  • Privacy Policy
  • Contact

© 2023 LBNN - All rights reserved.

No Result
View All Result
  • Home
  • Business
  • Politics
  • Markets
  • Crypto
  • Economics
    • Manufacturing
    • Real Estate
    • Infrastructure
  • Finance
  • Energy
  • Creator Economy
  • Wealth Management
  • Taxes
  • Telecoms
  • Military & Defense
  • Careers
  • Technology
  • Artificial Intelligence
  • Investigative journalism
  • Art & Culture
  • Documentaries
  • Quizzes
    • Enneagram quiz
  • Newsletters
    • LBNN Newsletter
    • Divergent Capitalist

© 2023 LBNN - All rights reserved.