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

Linearization and Approximation01:26

Linearization and Approximation

188
Linearization is a mathematical technique used to approximate complex, nonlinear functions with simpler linear models in the vicinity of a chosen reference point. The method is based on the idea that, although a function may be difficult to evaluate exactly, its behavior near a specific input value can often be closely approximated by the tangent line at that point. This approach is particularly useful when small deviations from a known value are involved.Consider the square root function, for...
188
Observational Learning01:12

Observational Learning

1.2K
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...
1.2K
Reinforcement01:23

Reinforcement

1.1K
Positive and negative reinforcement are key concepts in operant conditioning, a learning process where the consequences of a behavior affect the likelihood of that behavior being repeated.
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:
1.1K
Associative Learning01:27

Associative Learning

1.9K
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...
1.9K
Collisions in Multiple Dimensions: Problem Solving01:06

Collisions in Multiple Dimensions: Problem Solving

5.6K
In multiple dimensions, the conservation of momentum applies in each direction independently. Hence, to solve collisions in multiple dimensions, we should write down the momentum conservation in each direction separately. To help understand collisions in multiple dimensions, consider an example.
A small car of mass 1,200 kg traveling east at 60 km/h collides at an intersection with a truck of mass 3,000 kg traveling due north at 40 km/h. The two vehicles are locked together. What is the...
5.6K
Reconstruction of Signal using Interpolation01:10

Reconstruction of Signal using Interpolation

831
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next...
831

You might also read

Related Articles

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

Sort by
Same author

Colorimetric sensing array based on Fe single-atom nanozyme for ultrasensitively discriminating organophosphorus pesticides.

Analytica chimica acta·2026
Same author

WormSORT: A detection-based multiple object tracking model for individual silkworms in breeding environments.

PLoS computational biology·2026
Same author

Research and application of production release process optimization for low permeability condensate gas reservoirs in the East China Sea.

Scientific reports·2026
Same author

Development of a CRISPR/RspCas13d-based on-site rapid detection system for GII Norovirus.

Journal of virological methods·2026
Same author

Propranolol alleviates cerebral infarction through the β2-AR-mediated ERK/NLRP3 pathway.

iScience·2026
Same author

Research progress on chemical metabolites, processing technologies, and pharmacological activities of asperosaponin VI: a systematic review and critical evaluation.

Frontiers in pharmacology·2026

Related Experiment Video

Updated: Mar 26, 2026

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

859

Manifold-Based Reinforcement Learning via Locally Linear Reconstruction.

Xin Xu, Zhenhua Huang, Lei Zuo

    IEEE Transactions on Neural Networks and Learning Systems
    |February 2, 2016
    PubMed
    Summary

    This study introduces a novel manifold-based reinforcement learning (RL) approach using locally linear reconstruction (LLR) for complex control problems. The LLR-based method enhances feature learning and policy iteration, outperforming existing techniques in large state spaces.

    More Related Videos

    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

    1.3K

    Related Experiment Videos

    Last Updated: Mar 26, 2026

    Decoding Natural Behavior from Neuroethological Embedding
    08:00

    Decoding Natural Behavior from Neuroethological Embedding

    Published on: October 3, 2025

    859
    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

    1.3K

    Area of Science:

    • Machine Learning
    • Control Theory
    • Artificial Intelligence

    Background:

    • Feature representation is crucial for pattern recognition and reinforcement learning (RL) in control problems with uncertainties.
    • Markov decision processes (MDPs) with large or continuous state spaces pose significant challenges for traditional RL methods.
    • Effective feature learning is essential for accurate value function approximation in RL.

    Purpose of the Study:

    • To propose a manifold-based RL approach utilizing locally linear reconstruction (LLR) for MDPs with large or continuous state spaces.
    • To develop an LLR-based feature learning scheme for value function approximation in RL.
    • To design an LLR-based approximate policy iteration (API) algorithm for enhanced learning control.

    Main Methods:

    • Developed a feature learning scheme based on locally linear reconstruction (LLR) to generate smooth feature vectors.
    • Preserved local approximation properties of neighboring states in the original state space for feature generation.
    • Designed an LLR-based approximate policy iteration (API) algorithm for learning control in large/continuous state spaces.
    • Analyzed the relationship between value approximation error and nearest neighbor estimates.

    Main Results:

    • The LLR-based feature learning scheme effectively generates smooth feature vectors for value function approximation.
    • The LLR-based API algorithm demonstrated superior learning control performance compared to previous API methods.
    • Comprehensive simulations and experiments on benchmark problems validated the proposed approach across various parameter settings.

    Conclusions:

    • The proposed manifold-based RL approach with LLR offers a robust solution for learning control problems in large or continuous state spaces.
    • LLR-based feature learning significantly improves value function approximation and overall control performance in RL.
    • The LLR-based API algorithm represents a promising advancement for tackling complex control challenges in artificial intelligence.