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

Purposive Learning01:22

Purposive Learning

444
E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a...
444
Observational Learning01:12

Observational Learning

838
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...
838
Collisions in Multiple Dimensions: Problem Solving01:06

Collisions in Multiple Dimensions: Problem Solving

5.3K
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...
5.3K
Associative Learning01:27

Associative Learning

1.2K
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...
1.2K
Cognitive Learning01:21

Cognitive Learning

1.0K
Cognitive learning is based on purposive behavior, incidental learning, and insight learning.
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
1.0K
Machines: Problem Solving II01:30

Machines: Problem Solving II

647
Machines are complex structures consisting of movable, pin-connected multi-force members that work together to transmit forces. Consider a lifting tong carrying a 100 kg load. It comprises movable sections DAF and CBG linked together with member AB.
647

You might also read

Related Articles

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

Sort by
Same author

[Effects of Fe₃O₄ on the denitrification performance of Pseudomonas stutzeri].

Sheng wu gong cheng xue bao = Chinese journal of biotechnology·2021
Same author

Tumor-suppressive function of EZH2 is through inhibiting glutaminase.

Cell death & disease·2021
Same author

The K18-Human ACE2 Transgenic Mouse Model Recapitulates Non-severe and Severe COVID-19 in Response to an Infectious Dose of the SARS-CoV-2 Virus.

Journal of virology·2021
Same author

RUNX1 regulates the proliferation and chemoresistance of colorectal cancer through the Hedgehog signaling pathway.

Journal of Cancer·2021
Same author

Trimacrocyclic hexasubstituted benzene linked by labile octahedral [X(CHCl<sub>3</sub>)<sub>6</sub>]<sup>-</sup> clusters.

Chemical science·2021
Same author

An oncolytic virus expressing a full-length antibody enhances antitumor innate immune response to glioblastoma.

Nature communications·2021
Same journal

A practical design of backdoor trigger under frequency-based orthogonality constraints.

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

EEG fine-grained visual semantic decoding via a multimodal framework.

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

Collaborative-adversarial jailbreaking: A propagation-aware attack framework for multi-agent code generation systems.

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

Theoretical analysis of the denoising autoencoder using Tweedie's formula.

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

Frequency-based cross-attention fusion network for RGB-D salient object detection.

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

HTNet: A self-supervised heterogeneous triple network for multi-modal data.

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

Related Experiment Video

Updated: Jan 16, 2026

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy
11:53

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy

Published on: October 14, 2017

12.2K

Dual-driven optimization of collaborative multi-agent via case learning and curiosity.

Ruizhu Chen1, Rong Fei2, Junhuai Li2

  • 1School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, 710048, shaanxi, China.

Neural Networks : the Official Journal of the International Neural Network Society
|September 27, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a new method for multi-agent deep reinforcement learning (MADRL) that improves exploration and exploitation. The Case-Enhanced Random Network Distillation Exploration (CERE-CTDE) paradigm enhances learning efficiency and stability in complex scenarios.

Keywords:
Case-based reasoningCuriosity-drivenExploration-exploitation trade-offMulti-agent deep reinforcement learningStarcraft multi-agent challenge

Related Experiment Videos

Last Updated: Jan 16, 2026

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy
11:53

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy

Published on: October 14, 2017

12.2K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Robotics

Background:

  • Multi-Agent Deep Reinforcement Learning (MADRL) struggles with the exploration-exploitation trade-off during training.
  • Existing exploration methods often lack goal-direction, leading to inefficient data collection and unstable convergence.
  • Sparse rewards and the need for collaborative behavior present significant challenges in MADRL.

Purpose of the Study:

  • To propose a novel paradigm, Case-Enhanced Random Network Distillation Exploration for Centralized Training and Decentralized Execution (CERE-CTDE), to address MADRL training challenges.
  • To enhance the exploration-exploitation balance in MADRL through a synergistic integration of Random Network Distillation (RND) and Case-Based Reasoning (CBR).
  • To improve learning efficiency, policy convergence stability, and the ability to escape local optima in MADRL.

Main Methods:

  • Integration of Random Network Distillation (RND) for intrinsic motivation and enhanced exploration.
  • Incorporation of Case-Based Reasoning (CBR) for goal-directed exploitation by leveraging historical data.
  • Application of the CERE paradigm within the Centralized Training and Decentralized Execution (CTDE) framework for MADRL.

Main Results:

  • Demonstrated a statistically significant 17.97% improvement in win rate on complex StarCraft Multi-Agent Challenge (SMAC) scenarios.
  • Effectively enhanced policy exploration-exploitation and mitigated sparse reward issues via intrinsic motivation and CBR-guided action sampling.
  • Showcased superior capability in escaping local optima while maintaining high learning efficiency.

Conclusions:

  • The CERE-CTDE paradigm offers a robust solution for improving MADRL performance, particularly in environments with sparse rewards and complex interactions.
  • The dual mechanism of RND and CBR effectively balances exploration and exploitation, leading to more stable and efficient learning.
  • The framework's consistent performance across varying difficulty levels in SMAC validates its robustness and practical applicability.