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

Observational Learning01:12

Observational Learning

280
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...
280
Reinforcement01:23

Reinforcement

313
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:
313
Reinforcement Schedules01:24

Reinforcement Schedules

230
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,...
230
Avoidance Learning and Learned Helplessness01:14

Avoidance Learning and Learned Helplessness

1.9K
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...
1.9K
Associative Learning01:27

Associative Learning

523
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...
523
Collisions in Multiple Dimensions: Problem Solving01:06

Collisions in Multiple Dimensions: Problem Solving

4.3K
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...
4.3K

You might also read

Related Articles

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

Sort by
Same author

Effects of Bacillus velezensis SN-1 exopolysaccharide on the rheological properties of soy protein gel.

International journal of biological macromolecules·2026
Same author

Double encapsulation with porous starch and cellulose: A strategy for enhanced probiotic protection in microcapsules and tablets.

International journal of biological macromolecules·2026
Same author

Enzymatic modification of black bean dough: Mechanisms for enhancing physicochemical properties, noodle quality and frozen storage stability.

Food chemistry·2026
Same author

Association of neutrophil to lymphocyte ratio with the severity of coronary artery lesions in patients undergoing coronary angiography for the first time.

Cardiovascular diagnosis and therapy·2026
Same author

Semi-URF: Progressive Uncertainty-Aware Region Filtering and Fusion for Semi-Supervised Medical Image Segmentation.

IEEE journal of biomedical and health informatics·2026
Same author

Emulsifier-Modulated Microstructure of Soy Protein-Arabinoxylan Oleogels Improves Astaxanthin Bioaccessibility and In Vivo Antioxidant Activity.

Foods (Basel, Switzerland)·2026

Related Experiment Video

Updated: Aug 25, 2025

The HoneyComb Paradigm for Research on Collective Human Behavior
06:48

The HoneyComb Paradigm for Research on Collective Human Behavior

Published on: January 19, 2019

9.5K

A leader-following paradigm based deep reinforcement learning method for multi-agent cooperation games.

Feiye Zhang1, Qingyu Yang2, Dou An2

  • 1Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, No. 28, West Xianning Road, Xi'an, 710049, Shaanxi, PR China.

Neural Networks : the Official Journal of the International Neural Network Society
|October 13, 2022
PubMed
Summary

This study introduces a leader-following paradigm for multi-agent deep reinforcement learning, improving cooperation by allowing agents to specialize roles. The novel method enhances performance in cooperative games.

Keywords:
Centralized training with decentralized executionCooperative gamesDeep reinforcement learningMulti-agent systems

More Related Videos

The Collective Trust Game: An Online Group Adaptation of the Trust Game Based on the HoneyComb Paradigm
06:18

The Collective Trust Game: An Online Group Adaptation of the Trust Game Based on the HoneyComb Paradigm

Published on: October 20, 2022

2.2K
A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.5K

Related Experiment Videos

Last Updated: Aug 25, 2025

The HoneyComb Paradigm for Research on Collective Human Behavior
06:48

The HoneyComb Paradigm for Research on Collective Human Behavior

Published on: January 19, 2019

9.5K
The Collective Trust Game: An Online Group Adaptation of the Trust Game Based on the HoneyComb Paradigm
06:18

The Collective Trust Game: An Online Group Adaptation of the Trust Game Based on the HoneyComb Paradigm

Published on: October 20, 2022

2.2K
A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.5K

Area of Science:

  • Artificial Intelligence
  • Multi-Agent Systems
  • Deep Reinforcement Learning

Background:

  • Centralized Training with Decentralized Execution (CTDE) is a popular paradigm in multi-agent reinforcement learning.
  • Existing CTDE methods often overlook the heterogeneous roles of agents by having them act simultaneously.
  • This limitation hinders optimal cooperation in complex scenarios.

Purpose of the Study:

  • To propose a novel leader-following paradigm based deep multi-agent cooperation method (LFMCO).
  • To address the limitations of simultaneous action selection in CTDE.
  • To introduce a mechanism for agents to adopt specialized roles within cooperative tasks.

Main Methods:

  • Introduced a leader-following paradigm where a leader agent broadcasts actions to follower agents.
  • Follower agents select actions based on the leader's message and their own state.
  • Defined 'information gain' (change in follower value function entropy) to quantify leader influence.

Main Results:

  • LFMCO demonstrated significant performance improvements in cooperative scenarios.
  • Evaluated on StarCraft2 cooperative environments, showing superiority over state-of-the-art benchmarks.
  • The leader-following approach effectively handles heterogeneous agent roles.

Conclusions:

  • The leader-following paradigm offers a more effective approach to multi-agent cooperation than simultaneous action selection.
  • LFMCO enhances coordination by enabling specialized agent roles.
  • This method shows promise for complex multi-agent reinforcement learning tasks.