Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Hierarchy of Motor Control01:18

Hierarchy of Motor Control

5.6K
The hierarchy of motor control refers to the different levels of organization and processing involved in controlling movement in the body. These levels range from higher cortical areas involved in planning and decision-making to lower spinal cord reflexes that respond automatically to external stimuli.
5.6K
Stereotype Content Model02:16

Stereotype Content Model

13.1K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
13.1K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Unveiling Physical and Chemical Changes in All-Solid-State Battery: An Operando Synchrotron Chemical Imaging Study.

Small methods·2025
Same author

Accelerating the inference of string generation-based chemical reaction models for industrial applications.

Journal of cheminformatics·2025
Same author

emg2vec: Self-supervised Pretraining in Electromyography-based Silent Speech Interfaces.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

On the Distillation of Stories for Transferring Narrative Arcs in Collections of Independent Media.

IEEE transactions on pattern analysis and machine intelligence·2024
Same author

Interfacial Stabilization by Prelithiated Trithiocyanuric Acid as an Organic Additive in Sulfide-Based All-Solid-State Lithium Metal Batteries.

Angewandte Chemie (International ed. in English)·2024
Same author

Reagent prediction with a molecular transformer improves reaction data quality.

Chemical science·2023

Related Experiment Video

Updated: May 5, 2026

Investigating Motor Skill Learning Processes with a Robotic Manipulandum
07:52

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Published on: February 12, 2017

8.3K

Confidence-based progress-driven self-generated goals for skill acquisition in developmental robots.

Hung Ngo1, Matthew Luciw, Alexander Förster

  • 1IDSIA, Dalle Molle Institute for Artificial Intelligence, Università della Svizzera Italiana-Scuola Universitaria Professionale della Svizzera Italiana (USI-SUPSI) Lugano, Switzerland.

Frontiers in Psychology
|December 11, 2013
PubMed
Summary
This summary is machine-generated.

This study introduces a curiosity-driven reinforcement learning agent that learns skills without external rewards. The agent explores environments, identifies unknown instances, and generates plans, demonstrating continual learning and skill acquisition.

Keywords:
AI planningartificial curiositycontinual learningdevelopmental roboticsintrinsic motivationmarkov decision processesonline active learningsystematic exploration

More Related Videos

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy
11:53

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy

Published on: October 14, 2017

11.0K
Author Spotlight: Enhancing Post-Stroke Upper Limb Rehabilitation with Robotic Technologies for Improved Motor Recovery and Functional Outcomes
04:49

Author Spotlight: Enhancing Post-Stroke Upper Limb Rehabilitation with Robotic Technologies for Improved Motor Recovery and Functional Outcomes

Published on: September 6, 2024

1.7K

Related Experiment Videos

Last Updated: May 5, 2026

Investigating Motor Skill Learning Processes with a Robotic Manipulandum
07:52

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Published on: February 12, 2017

8.3K
The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy
11:53

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy

Published on: October 14, 2017

11.0K
Author Spotlight: Enhancing Post-Stroke Upper Limb Rehabilitation with Robotic Technologies for Improved Motor Recovery and Functional Outcomes
04:49

Author Spotlight: Enhancing Post-Stroke Upper Limb Rehabilitation with Robotic Technologies for Improved Motor Recovery and Functional Outcomes

Published on: September 6, 2024

1.7K

Area of Science:

  • Artificial Intelligence
  • Robotics
  • Machine Learning

Background:

  • Reinforcement learning agents often require external rewards for skill acquisition.
  • Continual learning and autonomous exploration are key challenges in artificial intelligence.

Purpose of the Study:

  • To develop a curiosity-driven exploration method for reinforcement learning agents.
  • To enable skill acquisition in agents without external rewards.
  • To formulate curiosity-driven learning as a selective sampling problem.

Main Methods:

  • A reinforcement learning agent uses a curiosity drive to explore its environment.
  • A query condition based on an online linear classifier identifies statistically unknown instances.
  • The agent queries unknown instances to improve its predictors and generates plans (skills) to reach new settings.

Main Results:

  • The proposed method demonstrates sample-efficient curious exploration.
  • The agent exhibits developmental stages, continual learning, and skill acquisition.
  • Validation on simulated and real robot arms shows the effectiveness of the approach.

Conclusions:

  • Curiosity-driven exploration can facilitate intrinsic motivation and skill acquisition in artificial agents.
  • The selective sampling formulation is effective for curiosity-driven learning.
  • The method shows promise for developing autonomous, learning agents.