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

Observational Learning01:12

Observational Learning

370
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
370

You might also read

Related Articles

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

Sort by
Same author

The impacts and potential affecting mechanism of pile-driving noise on metabolism of the thick-shell mussel Mytilus coruscus.

Environmental pollution (Barking, Essex : 1987)·2026
Same author

Unraveling hidden species diversity of talpid moles using phylogenomics and skull-based deep learning.

Communications biology·2026
Same author

Benzo[a]pyrene induces non-alcoholic fatty liver disease by exacerbating hepatic senescence and disrupting gut-liver axis in zebrafish.

Journal of hazardous materials·2026
Same author

Evaluation and comparison of TCR repertoire differences between patients with cervical cancer and healthy individuals.

Science China. Life sciences·2026
Same author

Transcriptomic insights into aerobic exercise-mediated attenuation of high-fat diet-induced muscle wasting.

Frontiers in physiology·2026
Same author

Knockout of the <i>C4BPA</i> Gene Promotes Mitophagy via Activation of the Pink1/Parkin Pathway and Alleviates the Inflammatory Response by Inhibiting the NF-κB Signalling Pathway in Bovine Mammary Epithelial Cells.

Veterinary sciences·2026
Same journal

RETRACTION: Multidimensional Heterogeneous Network Link Adaptation Based on Mobile Environment.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Framework to Segment and Evaluate Multiple Sclerosis Lesion in MRI Slices Using VGG-UNet.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Facial Emotion Recognition Using a Novel Fusion of Convolutional Neural Network and Local Binary Pattern in Crime Investigation.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Automatic Intelligent System Using Medical of Things for Multiple Sclerosis Detection.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Intangible Cultural Heritage Reproduction and Revitalization: Value Feedback, Practice, and Exploration Based on the IPA Model.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: CNN Based Multiclass Brain Tumor Detection Using Medical Imaging.

Computational intelligence and neuroscience·2025
See all related articles

Related Experiment Video

Updated: Oct 9, 2025

A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants
06:28

A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants

Published on: August 26, 2018

6.1K

Unbiased Model-Agnostic Metalearning Algorithm for Learning Target-Driven Visual Navigation Policy.

Tianfang Xue1,2,3,4, Haibin Yu1,2,3

  • 1State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China.

Computational Intelligence and Neuroscience
|December 20, 2021
PubMed
Summary
This summary is machine-generated.

Metalearning improves agent navigation but can overfit. This study introduces Unbiased Model-Agnostic Metalearning (UMAML) to enhance generalization in visual navigation by minimizing task loss inequality, outperforming existing methods.

More Related Videos

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
07:12

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

590
Integrating Visual Psychophysical Assays within a Y-Maze to Isolate the Role that Visual Features Play in Navigational Decisions
07:09

Integrating Visual Psychophysical Assays within a Y-Maze to Isolate the Role that Visual Features Play in Navigational Decisions

Published on: May 2, 2019

6.2K

Related Experiment Videos

Last Updated: Oct 9, 2025

A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants
06:28

A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants

Published on: August 26, 2018

6.1K
Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
07:12

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

590
Integrating Visual Psychophysical Assays within a Y-Maze to Isolate the Role that Visual Features Play in Navigational Decisions
07:09

Integrating Visual Psychophysical Assays within a Y-Maze to Isolate the Role that Visual Features Play in Navigational Decisions

Published on: May 2, 2019

6.2K

Area of Science:

  • Robotics
  • Artificial Intelligence
  • Computer Vision

Background:

  • Deep reinforcement learning has advanced visual navigation.
  • Metalearning algorithms enhance agent adaptability in new environments.
  • Overtraining metalearning models can hinder generalization in unfamiliar settings.

Purpose of the Study:

  • To propose an Unbiased Model-Agnostic Metalearning (UMAML) algorithm for target-driven visual navigation.
  • To enhance the generalization capability of navigation agents.
  • To train an impartial navigation model less biased by specific training environments.

Main Methods:

  • Developed the Unbiased Model-Agnostic Metalearning (UMAML) algorithm.
  • Utilized inequality measures from Economics to quantify and minimize loss deviation across tasks.
  • Implemented a balanced update rule for agent exploration and experience gathering.

Main Results:

  • The UMAML algorithm demonstrated superior generalization ability in visual navigation tasks.
  • Experimental results showed outperformance compared to state-of-the-art metalearning navigation methods.
  • The proposed method effectively mitigates bias towards specific training environments.

Conclusions:

  • UMAML enhances the generalization of visual navigation agents by learning an unbiased model.
  • Minimizing inequality in task losses is a key factor for improved adaptability.
  • The approach offers a more balanced and effective strategy for metalearning in navigation.