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

Associative Learning01:27

Associative Learning

636
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
636
Observational Learning01:12

Observational Learning

356
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...
356
Understanding Memory01:19

Understanding Memory

677
Memory is the retention of information or experiences over time, facilitated through three main processes: encoding, storage, and retrieval. Encoding is the process of inputting information into the memory system. For instance, when listening to a lecture, watching a play, reading a book, or having a conversation, the brain is actively encoding information. This initial stage involves transforming sensory input into a form that can be processed and stored by the brain. Various factors, such as...
677
Multicompartment Models: Overview01:14

Multicompartment Models: Overview

278
Multicompartment models are mathematical constructs that depict how drugs are distributed and eliminated within the body. They segment the body into several compartments, symbolizing various physiological or anatomical areas connected through drug transfer processes such as absorption, metabolism, distribution, and elimination.
These models offer a more comprehensive representation of drug behavior in the body than one-compartment models. They accommodate the complexity of drug distribution,...
278
Long-Term Memory01:18

Long-Term Memory

288
Long-term memory is a relatively permanent type of memory, capable of storing vast amounts of information over extended periods. Its storage capacity is generally considered unlimited.
Long-term memory can be categorized into two primary types: explicit and implicit memory. Explicit memory, also known as declarative memory, involves the conscious recollection of information that we deliberately try to remember, recall, and articulate. This type of memory encompasses specific facts, events, and...
288
Cognitive Learning01:21

Cognitive Learning

692
Cognitive learning is based on purposive behavior, incidental learning, and insight learning.
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
692

You might also read

Related Articles

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

Sort by
Same author

Event-triggered fuzzy logic control for an uncertain robot with coupled output constraints.

ISA transactions·2026
Same author

Window-to-window BEV representation learning for limited FoV cross-view geo-localization.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

ImagineNav++: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Nash Equilibrium Strategies for Multicluster Pursuit-Evasion Game With Disturbances: A Prescribed-Time Convergence Approach.

IEEE transactions on cybernetics·2026
Same author

Practical Prescribed-Time Cooperative Path Following of Underactuated Multi-ASVs Without Velocity Measurements via Intermittent Control.

IEEE transactions on cybernetics·2026
Same author

A modern look at simplicity bias in image classification tasks.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Hidden Data Recovery and Forecasting via Next-Generation Reservoir Computing With Multiscale Delay Selection.

IEEE transactions on neural networks and learning systems·2026
Same journal

CAFF-CIL: Causality-Aware Freedom Forgetting Approach for Class-Incremental Learning.

IEEE transactions on neural networks and learning systems·2026
Same journal

Harmonic Autoencoding Framework for Multiple Tasks in Magnetic Particle Imaging Reconstruction.

IEEE transactions on neural networks and learning systems·2026
Same journal

A Survey on Human-Centric Voice-Face Multimodal Learning.

IEEE transactions on neural networks and learning systems·2026
Same journal

Vision-Assisted Foundation Model for Solving Multitask Vehicle Routing Problems.

IEEE transactions on neural networks and learning systems·2026
Same journal

FP3O: Enabling Proximal Policy Optimization in Multiagent Cooperation With Parameter-Sharing Versatility.

IEEE transactions on neural networks and learning systems·2026
See all related articles

Related Experiment Video

Updated: Oct 1, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

704

Learning a World Model With Multitimescale Memory Augmentation.

Wenzhe Cai, Teng Wang, Jiawei Wang

    IEEE Transactions on Neural Networks and Learning Systems
    |March 7, 2022
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a novel neural network for model-based reinforcement learning (RL) that improves long-term prediction accuracy. The new approach enhances agent performance in complex environments by better managing short-term and long-term memory.

    More Related Videos

    Constructing and Visualizing Models using Mime-based Machine-learning Framework
    06:19

    Constructing and Visualizing Models using Mime-based Machine-learning Framework

    Published on: July 22, 2025

    928

    Related Experiment Videos

    Last Updated: Oct 1, 2025

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
    03:14

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

    Published on: December 6, 2024

    704
    Constructing and Visualizing Models using Mime-based Machine-learning Framework
    06:19

    Constructing and Visualizing Models using Mime-based Machine-learning Framework

    Published on: July 22, 2025

    928

    Area of Science:

    • Artificial Intelligence
    • Machine Learning
    • Robotics

    Background:

    • Model-based reinforcement learning (RL) shows promise but is limited by poor long-term prediction in high-dimensional state spaces.
    • Current dynamics prediction models struggle with accuracy over extended time horizons, hindering model-based RL effectiveness.

    Purpose of the Study:

    • To develop an improved dynamics prediction model for model-based RL that excels at long-term forecasting.
    • To enhance the performance of RL agents in complex, high-dimensional environments through accurate world modeling.

    Main Methods:

    • Proposed a novel two-branch neural network architecture incorporating multi-timescale memory augmentation.
    • Utilized a recurrent neural network for long-term memory encoding and a self-supervised optical flow structure for direct next-frame reconstruction (short-term memory).
    • Augmented reconstructed observations with long-term memory for semantic consistency.

    Main Results:

    • Achieved visually realistic and highly accurate long-term predictions in DeepMind maze navigation games.
    • Outperformed state-of-the-art methods in prediction accuracy by a significant margin.
    • Demonstrated the utility of the world model in an imagination-augmented exploration strategy for model-free RL controllers.

    Conclusions:

    • The proposed multi-timescale memory network effectively addresses the long-term prediction challenges in model-based RL.
    • This approach offers a significant advancement in world modeling for reinforcement learning, improving both prediction and exploration.