Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Reinforcement Schedules

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,...

Reinforcement

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:

Observational Learning

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...

You might also read

Related Articles

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

Sort by

Same author

ES-C51: Expected sarsa based C51 distributional reinforcement learning algorithm.

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

Same author

Evaluating digital health literacy interventions for adults 45+ years: a scoping review.

Health promotion international·2026

Same author

Towards a Broad-Persistent Advising Approach for Deep Interactive Reinforcement Learning in Robotic Environments.

Sensors (Basel, Switzerland)·2023

Same author

Event-Based Angular Speed Measurement and Movement Monitoring.

Sensors (Basel, Switzerland)·2022

Same author

Supporting Regional Aged Care Nursing Staff to Manage Residents' Behavioural and Psychological Symptoms of Dementia, in Real Time, Using the Nurses' Behavioural Assistant (NBA): A Pilot Site 'End-User Attitudes' Trial.

Studies in health technology and informatics·2018

Search research articles

Related Experiment Video

Updated: Nov 17, 2025

Automated Interactive Video Playback for Studies of Animal Communication

Automated Interactive Video Playback for Studies of Animal Communication

Published on: February 9, 2011

An Evaluation Methodology for Interactive Reinforcement Learning with Simulated Users.

Adam Bignold¹, Francisco Cruz^2,3, Richard Dazeley²

¹School of Engineering, Information Technology and Physical Sciences, Federation University Australia, Mount Helen, VIC 3350, Australia.

Biomimetics (Basel, Switzerland)

|February 12, 2021

Summary

This summary is machine-generated.

Simulated users offer an affordable and fast alternative for evaluating interactive reinforcement learning agents. This method provides insights into agent performance under various human constraints without costly real-world trials.

Keywords:

interactive reinforcement learning methodology for simulated users reinforcement learning reward shaping

More Related Videos

Behavioral Training Procedures for Head-fixed Virtual Reality in Mice

Behavioral Training Procedures for Head-fixed Virtual Reality in Mice

Published on: September 6, 2024

A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants

A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants

Published on: August 26, 2018

Related Experiment Videos

Last Updated: Nov 17, 2025

Automated Interactive Video Playback for Studies of Animal Communication

Automated Interactive Video Playback for Studies of Animal Communication

Published on: February 9, 2011

Behavioral Training Procedures for Head-fixed Virtual Reality in Mice

Behavioral Training Procedures for Head-fixed Virtual Reality in Mice

Published on: September 6, 2024

A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants

A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants

Published on: August 26, 2018

Area of Science:

Artificial Intelligence
Machine Learning
Reinforcement Learning

Background:

Interactive reinforcement learning (IRL) methods leverage external information to enhance agent learning.
Human advice significantly improves IRL agent performance.
Repeatedly requiring human interaction for IRL experiments is costly and introduces bias.

Purpose of the Study:

To introduce a methodology for evaluating IRL agents using simulated users.
To enable affordable and rapid testing of IRL agents under defined human constraints.
To analyze how different simulated user characteristics impact agent performance.

Main Methods:

Development of a methodology employing simulated users to mimic human knowledge and interaction.
Simulation of various user types to assess their influence on agent learning.
Experimental evaluation of IRL agent performance with simulated user assistance.

Main Results:

Simulated users provide a viable alternative to real human evaluators for IRL agents.
The methodology allows for preliminary evaluation and insight into agent performance variations.
Different simulated user characteristics demonstrably impact the learning agent's behavior.

Conclusions:

Simulated users offer a cost-effective and efficient approach for evaluating IRL agents.
This simulation-based methodology enhances understanding of IRL agent behavior under diverse advisory conditions.
The approach facilitates the development and testing of IRL agents by simulating human feedback.