Jove
Visualize
Contact Us

Related Concept Videos

Reinforcement Schedules01:24

Reinforcement Schedules

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,...
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
Reinforcement01:23

Reinforcement

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:
Trial and Error and Algorithm01:12

Trial and Error and Algorithm

A problem-solving strategy is a plan of action used to find a solution. Different strategies have distinct action plans. Trial and error involves trying different solutions until one works. For instance, to fix a broken printer, you might check ink levels, ensure the paper tray isn't jammed, and verify the printer's connection to your laptop. This method can be time-consuming but is commonly used. Thomas Edison, for example, used trial and error to find a suitable filament for the light bulb,...
Observational Learning01:12

Observational Learning

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 because...
Associative Learning01:27

Associative Learning

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...

You might also read

Related Articles

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

Sort by
Same author

Discovering state-of-the-art reinforcement learning algorithms.

Nature·2025
Same author

Deep Learning for Identification of Acute Illness and Facial Cues of Illness.

Frontiers in medicine·2021
Same author

Identifying and characterizing high-risk clusters in a heterogeneous ICU population with deep embedded clustering.

Scientific reports·2021
Same author

Ensemble machine learning prediction and variable importance analysis of 5-year mortality after cardiac valve and CABG operations.

Scientific reports·2021
Same author

A Bayesian Network Analysis of the Diagnostic Process and Its Accuracy to Determine How Clinicians Estimate Cardiac Function in Critically Ill Patients: Prospective Observational Cohort Study.

JMIR medical informatics·2019
Same author

Performance of neural networks for localizing moving objects with an artificial lateral line.

Bioinspiration & biomimetics·2017
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 Experiment Video

Updated: Jul 3, 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

Ensemble algorithms in reinforcement learning.

Marco A Wiering1, Hado van Hasselt

  • 1Department of Artificial Intelligence, University of Groningen, 9400 AK Groningen, The Netherlands. mwiering@ai.rug.nl

IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics : a Publication of the IEEE Systems, Man, and Cybernetics Society
|July 18, 2008
PubMed
Summary

This study introduces ensemble methods for reinforcement learning (RL) agents, combining multiple algorithms to boost performance. Boltzmann multiplication and majority voting ensembles significantly outperformed individual RL algorithms in maze tasks.

Related Experiment Videos

Last Updated: Jul 3, 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

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Reinforcement Learning

Background:

  • Reinforcement learning (RL) agents often struggle with learning speed and final performance.
  • Combining multiple RL algorithms into a single agent presents a potential solution.
  • Existing ensemble methods in RL primarily focus on learning a single value function.

Purpose of the Study:

  • To design and implement novel ensemble methods for combining diverse RL algorithms.
  • To enhance both the learning speed and final performance of RL agents.
  • To evaluate the effectiveness of these ensembles on various maze problems.

Main Methods:

  • Developed four distinct ensemble methods: majority voting (MV), rank voting, Boltzmann multiplication (BM), and Boltzmann addition.
  • Integrated five different RL algorithms: Q-learning, Sarsa, actor-critic (AC), QV-learning, and AC learning automaton.
  • Combined policies derived from the value functions of these diverse RL algorithms.

Main Results:

  • The Boltzmann multiplication (BM) and majority voting (MV) ensemble methods demonstrated significant performance improvements over individual RL algorithms.
  • Experiments were conducted on five maze problems, including dynamic and partially observable tasks.
  • The proposed ensemble approaches showed superior results compared to single RL algorithm implementations.

Conclusions:

  • Ensemble methods, particularly BM and MV, offer a promising approach to enhance RL agent capabilities.
  • Combining diverse RL algorithms through ensemble techniques can overcome limitations of individual algorithms.
  • The developed ensemble strategies are effective in complex and dynamic environments.