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

830
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:
830
Decision Making: P-value Method01:09

Decision Making: P-value Method

6.8K
The process of hypothesis testing based on the P-value method includes calculating the P- value using the sample data and interpreting it.
First, a specific claim about the population parameter is proposed. The claim is based on the research question and is stated in a simple form. Further, an opposing statement to the claim  is also stated. These statements can act as null and alternative hypotheses:  a null hypothesis would be a neutral statement while the alternative hypothesis can...
6.8K
Avoidance Learning and Learned Helplessness01:14

Avoidance Learning and Learned Helplessness

2.5K
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...
2.5K
Observational Learning01:12

Observational Learning

832
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...
832
Introduction to Learning01:18

Introduction to Learning

945
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...
945
Generalization, Discrimination, and Extinction01:24

Generalization, Discrimination, and Extinction

1.3K
Generalization, discrimination, and extinction are key concepts in operant conditioning that influence how behaviors are learned and maintained.
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
1.3K

You might also read

Related Articles

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

Sort by
Same author

Salvianolic Acid B Alleviates Atrial Fibrillation-Associated Fibrosis With Modulation of COL1A2 and the PI3K-AKT Pathway.

Cardiovascular therapeutics·2026
Same author

Tirzepatide monotherapy in Chinese patients with early type 2 diabetes: A randomized, double-blind, placebo-controlled phase 3 trial (SURPASS-CN-MONO).

Med (New York, N.Y.)·2026
Same author

HTD1801 in Combination with Metformin for Type 2 Diabetes.

NEJM evidence·2026
Same author

Efficacy of 12-week treatment with polyethylene glycol loxenatide in obesity or overweight patients with type 2 diabetes: a multicenter, prospective cohort study based on the flash glucose monitoring system.

Frontiers in endocrinology·2026
Same author

Dapagliflozin associates with heart rate variability decline in T2DM patients on GLP-1 receptor agonist therapy: a prospective observational study.

Frontiers in endocrinology·2026
Same author

Matching the Coupling of Valence Electrons in the Oxide Interface to Perturb the Magnetic Order Enhancing Oxygen Reduction in Zinc-Air Batteries.

Angewandte Chemie (International ed. in English)·2026

Related Experiment Videos

Recommendation of deep reinforcement learning based on value function considering error reduction.

JinLian Zhou1,2, DeRong Shen3, Ying Guo4

  • 1School of Computer Science and Engineering, Northeastern University, Shenyang, 110819, China. 543518214@qq.com.

Scientific Reports
|October 7, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces Q-AD, a novel algorithm for deep reinforcement learning recommender systems. Q-AD addresses action space reduction errors in Deep Q-Networks (DQN), improving accuracy for dynamic user preferences.

Keywords:
Knowledge graphProximal policy optimizationRecommendation systemReinforcement learning

Related Experiment Videos

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Recommender Systems

Background:

  • Deep reinforcement learning (DRL) captures dynamic user preferences in recommender systems.
  • Deep Q-Networks (DQN) are popular but struggle with gradually shrinking action spaces in cold-start scenarios.
  • Existing DQN methods cause discrepancies leading to Q-value estimation errors.

Purpose of the Study:

  • To address the action space reduction error in DQN-based recommender systems.
  • To improve the accuracy and efficiency of reinforcement learning in scenarios with dynamic action spaces.
  • To mitigate Q-value estimation inaccuracies caused by discrepancies between fixed and shrinking action spaces.

Main Methods:

  • Introduced Q-AD (Q-learning Action Decrease), a novel algorithm based on DQN.
  • Q-AD buffers Q-value estimation errors at each update to mitigate reduction errors.
  • Augmented standard DQN with an error reduction term for temporal difference (TD) updates.

Main Results:

  • Q-AD significantly reduces value estimation errors compared to standard DQN.
  • The proposed algorithm achieves better accuracy and efficiency across various datasets.
  • Demonstrated improved performance in long-term recommendation scenarios with varying interaction lengths.

Conclusions:

  • Q-AD effectively mitigates action space reduction errors in DQN-based recommender systems.
  • The algorithm enhances the accuracy and efficiency of Q-value estimation.
  • Q-AD offers a more robust solution for user cold-start scenarios with gradually reducing action spaces.