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

Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

203
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence...
203
Avoidance Learning and Learned Helplessness01:14

Avoidance Learning and Learned Helplessness

2.0K
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...
2.0K
Collisions in Multiple Dimensions: Problem Solving01:06

Collisions in Multiple Dimensions: Problem Solving

4.6K
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...
4.6K
Reinforcement01:23

Reinforcement

466
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:
466
Observational Learning01:12

Observational Learning

390
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...
390
Reinforcement Schedules01:24

Reinforcement Schedules

270
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,...
270

You might also read

Related Articles

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

Sort by
Same author

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 author

Factors associated with cancer-related fatigue in advanced hepatocellular carcinoma patients during the peri-intervention period: a path analysis model.

Scientific reports·2026
Same author

Expression of PIEZO1 in lung adenocarcinoma correlates with PD-L1 expression, cell migration, and poor prognosis: an exploratory study.

Discover oncology·2026
Same author

Anti-PD-1 monoclonal antibody suppresses hepatitis B virus in patients with hepatocellular carcinoma.

Chinese medical journal·2026
Same author

First-Line Pembrolizumab Plus Chemotherapy for Advanced Biliary Tract Cancer: China Subgroup Analysis of the Randomized Phase 3 KEYNOTE-966 Study.

Advances in therapy·2026
Same author

On the Two Facets to Conquer Wild Out-of-Distribution Detection.

IEEE transactions on pattern analysis and machine intelligence·2026

Related Experiment Video

Updated: Oct 18, 2025

A Modified Lean and Release Technique to Emphasize Response Inhibition and Action Selection in Reactive Balance
07:19

A Modified Lean and Release Technique to Emphasize Response Inhibition and Action Selection in Reactive Balance

Published on: March 19, 2020

6.0K

Attention-Based Fault-Tolerant Approach for Multi-Agent Reinforcement Learning Systems.

Shanzhi Gu1, Mingyang Geng1, Long Lan2

  • 1College of Computer, National University of Defense Technology, Changsha 410073, China.

Entropy (Basel, Switzerland)
|September 28, 2021
PubMed
Summary

This study introduces an Attention-based Fault-Tolerant (FT-Attn) model for multi-agent reinforcement learning systems facing malicious agents. FT-Attn enhances agent coordination in noisy environments without needing prior knowledge of noise intensity.

Keywords:
attention mechanismfault tolerancemulti-agentreinforcement learning

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.4K
WheelCon: A Wheel Control-Based Gaming Platform for Studying Human Sensorimotor Control
08:18

WheelCon: A Wheel Control-Based Gaming Platform for Studying Human Sensorimotor Control

Published on: August 15, 2020

5.1K

Related Experiment Videos

Last Updated: Oct 18, 2025

A Modified Lean and Release Technique to Emphasize Response Inhibition and Action Selection in Reactive Balance
07:19

A Modified Lean and Release Technique to Emphasize Response Inhibition and Action Selection in Reactive Balance

Published on: March 19, 2020

6.0K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.4K
WheelCon: A Wheel Control-Based Gaming Platform for Studying Human Sensorimotor Control
08:18

WheelCon: A Wheel Control-Based Gaming Platform for Studying Human Sensorimotor Control

Published on: August 15, 2020

5.1K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Robotics

Background:

  • Multi-agent reinforcement learning (MARL) enables agents to learn collaboratively.
  • Realistic MARL scenarios involve partial observability and potential agent failures.
  • Existing methods struggle with unknown or changing noise levels in environments.

Purpose of the Study:

  • To develop a robust MARL system resilient to faulty or malicious agents.
  • To address limitations of prior work that required known noise intensity.
  • To improve coordination and learning in harsh, unpredictable environments.

Main Methods:

  • Proposed an Attention-based Fault-Tolerant (FT-Attn) model.
  • Utilized a multihead attention mechanism for selective information processing.
  • Enabled agents to learn communication and action policies concurrently.

Main Results:

  • FT-Attn outperformed state-of-the-art methods in extremely noisy cooperative and competitive scenarios.
  • The model achieved performance closer to the theoretical upper bound.
  • Demonstrated general fault tolerance without prior noise intensity knowledge.

Conclusions:

  • The FT-Attn model offers a significant advancement in robust MARL.
  • It provides practical fault tolerance in dynamic and adversarial environments.
  • Eliminates the need for pre-defined noise intensity parameters, enhancing applicability.