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

Self-Discrepancy and Its Effects01:29

Self-Discrepancy and Its Effects

463
Self-discrepancy theory explains how people compare their actual self to their ideal and ought selves and how mismatches between these self-guides can lead to emotional distress. Developed by E. Tory Higgins, the theory distinguishes among three components of self-concept: the actual self, the ideal self, and the ought self. These refer respectively to how individuals perceive themselves, how they aspire to be, and how they believe they are obligated to be. Emotional well-being, self-esteem,...
463
Self-Discrepancy Theory02:45

Self-Discrepancy Theory

19.1K
One influential perspective on what motivates people's behavior is detailed in Tory Higgin's self-discrepancy theory (Higgins, 1987). He proposed that people hold disagreeing internal representations of themselves that lead to different emotional states.  
19.1K
Causes of Similarity-Dissimilarity Effect01:26

Causes of Similarity-Dissimilarity Effect

351
The similarity-dissimilarity effect, a fundamental concept in social psychology, explains how interpersonal similarities and differences influence attraction and social interactions. This effect is supported by three key psychological perspectives: balance theory, social comparison theory, and consensual validation.Balance Theory and Cognitive ConsistencyBalance theory, developed by Fritz Heider, posits that individuals seek cognitive consistency in their relationships. When two people share...
351
Decision Making: P-value Method01:09

Decision Making: P-value Method

7.4K
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...
7.4K
Variability: Analysis01:11

Variability: Analysis

777
Measures of variability are statistical metrics that reveal the dispersion pattern within a dataset. They are pivotal in biostatistics, providing insights into the heterogeneity within health and biological data. Variability signifies the degree to which data points diverge from one another, helping researchers understand the potential range of values and associated uncertainty within the data.
The range is a simple measure of variability, indicating the difference between the highest and...
777
Masking and Demasking Agents01:19

Masking and Demasking Agents

4.0K
EDTA titrations may necessitate masking and demasking agents to temporarily protect a particular metal ion in a mixture from the EDTA reaction. These agents facilitate the sequential analysis of the metal ions by forming stable complexes with some—but not all—metal ions during certain steps.
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on...
4.0K

You might also read

Related Articles

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

Sort by
Same author

Optimization of Andrographolide Nanocrystal-loaded Liposomes by Box-Behnken Design and its <i>In vitro</i> and <i>In vivo</i> Evaluation.

Current drug delivery·2026
Same author

Approaches for enhancing bioavailability of macromolecular drugs.

International journal of pharmaceutics·2026
Same author

Tanshinone IIA suppresses cancer metastasis by modulating tumor cell-platelet-endothelial cell interactions.

Oncology letters·2026
Same author

Mechanisms influencing adult children's willingness to use medical visit accompaniment services for older adults in Nanjing: a structural equation modeling study.

Frontiers in public health·2026
Same author

High-fidelity compressed high-speed imaging for resolving rapid micro-dynamics.

Optics express·2026
Same author

Diagnostic performance of controlled attenuation parameter for grading hepatic steatosis in MASLD: an MRI-PDFF-referenced study in a Chinese cohort.

Frontiers in medicine·2026
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

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

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

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

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

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

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

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

Aggregating global-scale pixel-wise forgery cues within a graph.

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

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

Related Experiment Video

Updated: Apr 16, 2026

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models
07:14

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models

Published on: December 23, 2025

867

Multi-agent contrastive exploration via value decomposition discrepancy.

Siying Wang1, Hongfei Du2, Chiyu Cai3

  • 1School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China; College of Computer Science and Artificial Intelligence, Southwest Minzu University, Chengdu, China; Intelligent Perception and Control Key Laboratory of Sichuan Province, Sichuan University of Science & Engineering, Zigong, China.

Neural Networks : the Official Journal of the International Neural Network Society
|April 14, 2026
PubMed
Summary
This summary is machine-generated.

This study introduces Multi-Agent Contrastive Exploration (MACE) to improve multi-agent reinforcement learning (MARL) by leveraging value decomposition discrepancies for enhanced exploration and learning speed.

Keywords:
Deep reinforcement learningExploration and exploitationMulti-agent cooperationValue decomposition

More Related Videos

Decomposing the Variance in Reading Comprehension to Reveal the Unique and Common Effects of Language and Decoding
06:33

Decomposing the Variance in Reading Comprehension to Reveal the Unique and Common Effects of Language and Decoding

Published on: October 11, 2018

7.3K
Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language
09:27

Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language

Published on: October 13, 2018

10.9K

Related Experiment Videos

Last Updated: Apr 16, 2026

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models
07:14

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models

Published on: December 23, 2025

867
Decomposing the Variance in Reading Comprehension to Reveal the Unique and Common Effects of Language and Decoding
06:33

Decomposing the Variance in Reading Comprehension to Reveal the Unique and Common Effects of Language and Decoding

Published on: October 11, 2018

7.3K
Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language
09:27

Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language

Published on: October 13, 2018

10.9K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Multi-Agent Systems

Background:

  • Value decomposition is crucial for multi-agent reinforcement learning (MARL) but often faces challenges with sample efficiency and limited representation capability.
  • Existing methods may struggle to enable agents to discover optimal joint actions due to representational constraints.

Purpose of the Study:

  • To enhance agent exploration in MARL by addressing limitations in value decomposition.
  • To develop a method that improves learning speed and final performance in complex multi-agent tasks.

Main Methods:

  • Proposes Multi-Agent Contrastive Exploration (MACE), a novel method leveraging value decomposition discrepancies and contrastive principles.
  • MACE utilizes discrepancies between value decomposition estimates to set update weights and introduces this difference as an intrinsic target.
  • Introduces an exploration preference network inspired by value discrepancies to adjust agent exploration strategies.

Main Results:

  • MACE significantly outperforms baseline methods in both learning speed and final performance across various Matrix Games and Starcraft Multi-Agent Challenge tasks.
  • The method effectively maintains higher expressivity compared to existing approaches.
  • Demonstrates improved sample efficiency and exploration capabilities in multi-agent settings.

Conclusions:

  • MACE offers an innovative solution integrating the advantages of existing MARL algorithms.
  • The proposed method enhances exploration and representation capabilities, leading to superior performance in complex multi-agent scenarios.
  • MACE represents a significant advancement in value-based MARL by effectively addressing sample efficiency and optimal action discovery challenges.