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

134
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...
134
Observational Learning01:12

Observational Learning

246
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...
246
Predicting Reaction Outcomes02:24

Predicting Reaction Outcomes

8.5K
Kinetics describes the rate and path by which a reaction occurs. In contrast, thermodynamics deals with state functions and describes the properties, behavior, and components of a system. It is not concerned with the path taken by the process and cannot address the rate at which a reaction occurs. Although it does provide information about what can happen during a reaction process, it does not describe the detailed steps of what appears on an atomic or a molecular level. On the other hand,...
8.5K
Associative Learning01:27

Associative Learning

465
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...
465
Attribution Theory00:56

Attribution Theory

13.1K
Behavior is a product of both the situation (e.g., cultural influences, social roles, and the presence of bystanders) and of the person (e.g., personality characteristics). Subfields of psychology tend to focus on one influence or behavior over others. Situationism is the view that our behavior and actions are determined by our immediate environment and surroundings. In contrast, dispositionism holds that our behavior is determined by internal factors (Heider, 1958).
13.1K
Reinforcement01:23

Reinforcement

295
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:
295

You might also read

Related Articles

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

Sort by
Same author

Long-Lived Phosphorescent CDs@SiO<sub>2</sub> Coupled with Magnetic Quencher Fe<sub>3</sub>O<sub>4</sub>@PDA: A Dual-Mode Lateral Flow Immunochromatographic Assay for Sensitive Determination of Acetamiprid.

Analytical chemistry·2026
Same author

Deep learning of 2D-Restructured gene expression representations for improved low-sample therapeutic response prediction.

Computers in biology and medicine·2023
Same author

Structural and expression analysis of the dopamine receptors reveals their crucial roles in regulating the insulin signaling pathway in oysters.

International journal of biological macromolecules·2023
Same author

Huobahuagen tablet improves renal function in diabetic kidney disease: a real-world retrospective cohort study.

Frontiers in endocrinology·2023
Same author

C-terminal tensin-like (<i>CTEN</i>) knockin alleviates cystic kidney defects in <i>Tensin-1</i> knockout mice.

Genes & diseases·2023
Same author

Enhanced Electron Transport in Nonconjugated Radical Oligomers Occurs by Tunneling.

Nano letters·2023

Related Experiment Video

Updated: Jul 28, 2025

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

3.9K

Credit assignment with predictive contribution measurement in multi-agent reinforcement learning.

Renlong Chen1, Ying Tan2

  • 1School of Intelligence Science and Technology, Peking University, Beijing, 100871, China.

Neural Networks : the Official Journal of the International Neural Network Society
|May 31, 2023
PubMed
Summary

This study presents Predictive Contribution Measurement, a novel credit assignment method for multi-agent reinforcement learning. PC-MAPPO enhances policy gradient methods, outperforming existing approaches in complex cooperative tasks.

Keywords:
Centralized training with decentralized execution (CTDE)Credit assignmentMulti-agent reinforcement learning (MARL)Policy gradientReward reshaping

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

8.8K
Characterization of the Sense of Agency over the Actions of Neural-machine Interface-operated Prostheses
05:21

Characterization of the Sense of Agency over the Actions of Neural-machine Interface-operated Prostheses

Published on: January 7, 2019

8.0K

Related Experiment Videos

Last Updated: Jul 28, 2025

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

3.9K
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

8.8K
Characterization of the Sense of Agency over the Actions of Neural-machine Interface-operated Prostheses
05:21

Characterization of the Sense of Agency over the Actions of Neural-machine Interface-operated Prostheses

Published on: January 7, 2019

8.0K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Reinforcement Learning

Background:

  • Credit assignment is challenging in multi-agent systems using centralized training and decentralized execution.
  • Value decomposition methods work well for Q-learning but struggle with policy gradient methods.
  • Existing methods face limitations in efficiently assigning credit in complex multi-agent scenarios.

Purpose of the Study:

  • To introduce Predictive Contribution Measurement (PCM), an explicit credit assignment method for multi-agent tasks.
  • To develop Predictive Contribution Multi-Agent Proximal Policy Optimization (PC-MAPPO) by integrating PCM with MAPPO.
  • To provide a theoretical guarantee for the proposed credit assignment mechanism.

Main Methods:

  • Developed Predictive Contribution Measurement (PCM) by comparing agent prediction errors.
  • Allocated surrogate rewards based on agent relevance to global state transitions.
  • Integrated PCM into the Multi-Agent Proximal Policy Optimization (MAPPO) framework, creating PC-MAPPO.
  • Utilized a pre-trained predictor for enhanced performance.

Main Results:

  • PC-MAPPO demonstrated superior performance over MAPPO, QMIX, and Weighted QMIX on StarCraft multi-agent challenge maps.
  • Significant performance gains were observed on maps demanding high levels of cooperation.
  • PC-MAPPO achieved state-of-the-art results with improved data efficiency in parallel training.

Conclusions:

  • Predictive Contribution Measurement offers an effective solution for credit assignment in policy gradient-based multi-agent reinforcement learning.
  • PC-MAPPO significantly enhances cooperative task performance, especially in challenging scenarios.
  • The proposed method shows promise for advancing multi-agent reinforcement learning research and applications.