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

Reinforcement01:23

Reinforcement

152
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:
152
Reinforcement Schedules01:24

Reinforcement Schedules

115
Positive reinforcement is a powerful method for teaching new behaviors to both animals and humans. B.F. Skinner demonstrated this with his experiments using rats in a Skinner box. When a rat pressed a lever, it received a food pellet. This immediate reward encouraged the rat to repeat the behavior. This method, where a reward follows every instance of the behavior, is known as continuous reinforcement. It is highly effective for establishing new behaviors quickly.
Once a behavior is learned,...
115
Observational Learning01:12

Observational Learning

98
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...
98
Associative Learning01:27

Associative Learning

239
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...
239
Introduction to Learning01:18

Introduction to Learning

302
Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
302
Avoidance Learning and Learned Helplessness01:14

Avoidance Learning and Learned Helplessness

1.7K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
1.7K

You might also read

Related Articles

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

Sort by
Same author

Antioxidant lipid nanoparticles enhance mRNA stability for regeneration therapy and gene editing.

Nature communications·2026
Same author

Epigallocatechin-3-Gallate Suppresses Glioma by Targeting Integrin αvβ3/FAK/ERK Signaling Axis and Matrix Metalloproteinases.

Phytotherapy research : PTR·2026
Same author

Rational design of rigid mRNA folding architecture to enhance intracellular processing and protein production.

Nature nanotechnology·2026
Same author

Removal of expression of concern: A hypoxia-dissociable siRNA nanoplatform for synergistically enhanced chemo-radiotherapy of glioblastoma.

Biomaterials science·2025
Same author

Targeting GOLPH3L improves glioblastoma radiotherapy by regulating STING-NLRP3-mediated tumor immune microenvironment reprogramming.

Science translational medicine·2025
Same author

Bulk and single-cell transcriptome revealed the metabolic heterogeneity in human glioma.

Heliyon·2025

Related Experiment Video

Updated: May 10, 2025

An Open-Source Virtual Reality System for the Measurement of Spatial Learning in Head-Restrained Mice
08:59

An Open-Source Virtual Reality System for the Measurement of Spatial Learning in Head-Restrained Mice

Published on: March 3, 2023

1.9K

From Task Distributions to Expected Paths Lengths Distributions: Value Function Initialization in Sparse Reward

Soumia Mehimeh1, Xianglong Tang1

  • 1School of Computer Science and Technology, Harbin Institute of Technology, 92 West Dazhi Street, Nangang District, Harbin 150001, China.

Entropy (Basel, Switzerland)
|April 26, 2025
PubMed
Summary

This study introduces LogQInit, a novel method for value function transfer in reinforcement learning. It leverages the log-normal distribution of value functions for improved performance in sparse reward environments with changing tasks.

Keywords:
lifelong learningreinforcement learningstatistical reinforcement learningvalue function initialization

More Related Videos

Pavlovian Conditioned Approach Training in Rats
06:57

Pavlovian Conditioned Approach Training in Rats

Published on: February 4, 2016

10.9K
Recording Single Neurons' Action Potentials from Freely Moving Pigeons Across Three Stages of Learning
11:20

Recording Single Neurons' Action Potentials from Freely Moving Pigeons Across Three Stages of Learning

Published on: June 2, 2014

11.9K

Related Experiment Videos

Last Updated: May 10, 2025

An Open-Source Virtual Reality System for the Measurement of Spatial Learning in Head-Restrained Mice
08:59

An Open-Source Virtual Reality System for the Measurement of Spatial Learning in Head-Restrained Mice

Published on: March 3, 2023

1.9K
Pavlovian Conditioned Approach Training in Rats
06:57

Pavlovian Conditioned Approach Training in Rats

Published on: February 4, 2016

10.9K
Recording Single Neurons' Action Potentials from Freely Moving Pigeons Across Three Stages of Learning
11:20

Recording Single Neurons' Action Potentials from Freely Moving Pigeons Across Three Stages of Learning

Published on: June 2, 2014

11.9K

Area of Science:

  • Reinforcement Learning
  • Artificial Intelligence
  • Machine Learning

Background:

  • Value function transfer is crucial for efficient reinforcement learning (RL) in tasks with changing goals or dynamics.
  • Environments with sparse rewards and terminal goals present significant challenges for traditional RL methods.

Purpose of the Study:

  • To propose a novel theoretical framework for understanding value function distribution in RL.
  • To introduce an efficient value function transfer method, LogQInit, for sparse reward environments.

Main Methods:

  • Theoretically reformulated value function distribution as expected optimal path length distribution.
  • Hypothesized and validated a normal distribution for expected optimal path lengths.
  • Proposed a log-normal distribution for value functions based on theoretical insights.
  • Developed and experimentally validated the LogQInit method.

Main Results:

  • Demonstrated that value function distribution can be characterized by expected optimal path length distribution.
  • Validated the log-normal property of value functions under specific task distributions.
  • LogQInit significantly outperformed existing methods in value function initialization and transfer.

Conclusions:

  • The proposed log-normal distribution provides a robust theoretical foundation for value function transfer.
  • LogQInit offers a more effective approach for RL agents operating in dynamic, sparse reward settings.
  • This work advances the field of transfer learning in reinforcement learning.