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

Collisions in Multiple Dimensions: Problem Solving01:06

Collisions in Multiple Dimensions: Problem Solving

4.2K
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...
4.2K
Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

106
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...
106
Reinforcement Schedules01:24

Reinforcement Schedules

148
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,...
148
Associative Learning01:27

Associative Learning

375
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...
375
Coordination Number and Geometry02:57

Coordination Number and Geometry

15.8K
For transition metal complexes, the coordination number determines the geometry around the central metal ion. Table 1 compares coordination numbers to molecular geometry. The most common structures of the complexes in coordination compounds are octahedral, tetrahedral, and square planar.
15.8K
Collisions in Multiple Dimensions: Introduction01:05

Collisions in Multiple Dimensions: Introduction

5.4K
It is far more common for collisions to occur in two dimensions; that is, the initial velocity vectors are neither parallel nor antiparallel to each other. Let's see what complications arise from this. The first idea is that momentum is a vector. Like all vectors, it can be expressed as a sum of perpendicular components (usually, though not always, an x-component and a y-component, and a z-component if necessary). Thus, when the statement of conservation of momentum is written for a...
5.4K

You might also read

Related Articles

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

Sort by
Same author

superLPNet: a super lightweight parameter deep learning model for brain age estimation from structural MRI.

Magma (New York, N.Y.)·2026
Same author

MDFNet: a multi-dimensional feature fusion model based on structural magnetic resonance imaging representations for brain age estimation.

Magma (New York, N.Y.)·2025
Same author

Iterated Clique Reductions in Vertex Weighted Coloring for Large Sparse Graphs.

Entropy (Basel, Switzerland)·2023
Same author

Synergistic Effect of Lenvatinib and Chemotherapy in Hepatocellular Carcinoma Using Preclinical Models.

Journal of hepatocellular carcinoma·2023
Same author

Coupling annealed silver nanoparticles with a porous silicon Bragg mirror SERS substrate and machine learning for rapid non-invasive disease diagnosis.

Analytica chimica acta·2023
Same author

Effectiveness and Safety of Belimumab in Chinese Lupus Patients: A Multicenter, Real-World Observational Study.

Biomedicines·2023

Related Experiment Video

Updated: Jul 5, 2025

Real-Time Proxy-Control of Re-Parameterized Peripheral Signals using a Close-Loop Interface
11:54

Real-Time Proxy-Control of Re-Parameterized Peripheral Signals using a Close-Loop Interface

Published on: May 8, 2021

4.4K

Coordination as inference in multi-agent reinforcement learning.

Zhiyuan Li1, Lijun Wu1, Kaile Su2

  • 1School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China.

Neural Networks : the Official Journal of the International Neural Network Society
|January 17, 2024
PubMed
Summary
This summary is machine-generated.

We introduce Deep Motor System (DMS), an inference-based method for multi-agent reinforcement learning (MARL). DMS enables agents to coordinate effectively using only local information, overcoming limitations of centralized training decentralized execution and independent learning.

Keywords:
Causal inferenceDeep reinforcement learningMulti-agent SystemNon-stationaryTheory of mindVariational inference

More Related Videos

Investigating Motor Skill Learning Processes with a Robotic Manipulandum
07:52

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Published on: February 12, 2017

8.7K
A Fully Automated Rodent Conditioning Protocol for Sensorimotor Integration and Cognitive Control Experiments
09:43

A Fully Automated Rodent Conditioning Protocol for Sensorimotor Integration and Cognitive Control Experiments

Published on: April 15, 2014

10.6K

Related Experiment Videos

Last Updated: Jul 5, 2025

Real-Time Proxy-Control of Re-Parameterized Peripheral Signals using a Close-Loop Interface
11:54

Real-Time Proxy-Control of Re-Parameterized Peripheral Signals using a Close-Loop Interface

Published on: May 8, 2021

4.4K
Investigating Motor Skill Learning Processes with a Robotic Manipulandum
07:52

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Published on: February 12, 2017

8.7K
A Fully Automated Rodent Conditioning Protocol for Sensorimotor Integration and Cognitive Control Experiments
09:43

A Fully Automated Rodent Conditioning Protocol for Sensorimotor Integration and Cognitive Control Experiments

Published on: April 15, 2014

10.6K

Area of Science:

  • Artificial Intelligence
  • Reinforcement Learning
  • Multi-Agent Systems

Background:

  • Centralized Training Decentralized Execution (CTDE) advances MARL but suffers from Centralized-Decentralized Mismatch (CDM).
  • Fully decentralized Independent Learning (IL) mimics natural cooperation but lacks agent awareness and coordination mechanisms.

Purpose of the Study:

  • To propose an inference-based coordinated MARL method, Deep Motor System (DMS).
  • To address agent awareness and coordination challenges within the Independent Learning (IL) paradigm.

Main Methods:

  • DMS utilizes individual intention inference, allowing agents to distinguish other agents from their environment.
  • Causal inference is employed to enhance coordination by reasoning about agent effects on each other's behavior.

Main Results:

  • DMS was evaluated on Multi-Agent MuJoCo and StarCraftII tasks.
  • The proposed method demonstrated superior performance compared to Independent Learning (IL) algorithms.
  • DMS successfully learned coordination behavior without relying on the CTDE paradigm, outperforming baselines like IPPO and HAPPO.

Conclusions:

  • DMS offers an effective approach to MARL coordination, particularly in decentralized settings.
  • The method overcomes limitations of CTDE and enhances IL by incorporating intention and causal inference.
  • DMS facilitates robust coordination in multi-agent systems without centralized training information.