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

Reinforcement Schedules01:24

Reinforcement Schedules

351
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,...
351
Role of Shaping in Operant Conditioning01:19

Role of Shaping in Operant Conditioning

775
Shaping is a technique used in operant conditioning to train complex behaviors by rewarding successive approximations toward the target behavior. This method is necessary because organisms are unlikely to perform complex behaviors spontaneously. Instead, shaping breaks down the desired behavior into small, manageable steps.
The steps involved in shaping begin with reinforcing any response that resembles the desired behavior. For example, parents might praise a child for picking up one toy. As...
775
Decision Making: Traditional Method01:14

Decision Making: Traditional Method

4.9K
The process of hypothesis testing based on the traditional method includes calculating the critical value, testing the value of the test statistic using the sample data, and interpreting these values.
First, a specific claim about the population parameter is decided based on the research question and is stated in a simple form. Further, an opposing statement to this claim is also stated. These statements can act as null and alternative hypotheses, out of which a null hypothesis would be a...
4.9K
Reinforcement01:23

Reinforcement

656
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:
656

You might also read

Related Articles

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

Sort by
Same author

Closed-loop Control for a Heterogeneous Group of Magnetically-actuated Microrobots.

... International Conference on Manipulation Automation and Robotics at Small Scales (MARSS). International Conference on Manipulation Automation and Robotics at Small Scales·2024
Same author

Algorithms for Autonomous Formation of Multicellular Shapes from Single Cells.

ACS synthetic biology·2024
Same author

Learning a Tracking Controller for Rolling <i>μ</i>bots.

IEEE robotics and automation letters·2024
Same author

How Retroactivity Affects the Behavior of Incoherent Feedforward Loops.

iScience·2020
Same author

Automated Design of Pluripotent Stem Cell Self-Organization.

Cell systems·2019
Same author

Modeling Genetic Circuit Behavior in Transiently Transfected Mammalian Cells.

ACS synthetic biology·2019

Related Experiment Video

Updated: Dec 2, 2025

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

9.0K

A formal methods approach to interpretable reinforcement learning for robotic planning.

Xiao Li1, Zachary Serlin2, Guang Yang3

  • 1Department of Mechanical Engineering, Boston University, Boston, MA, USA. xli87@bu.edu.

Science Robotics
|November 2, 2020
PubMed
Summary

This study introduces a formal methods approach to reinforcement learning for robots, ensuring predictable and safe behaviors. It integrates task specifications with domain knowledge, guaranteeing safety while guiding policy generation.

More Related Videos

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

12.0K
SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots
11:01

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

Published on: November 24, 2015

13.5K

Related Experiment Videos

Last Updated: Dec 2, 2025

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

9.0K
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

12.0K
SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots
11:01

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

Published on: November 24, 2015

13.5K

Area of Science:

  • Robotics
  • Artificial Intelligence
  • Formal Methods

Background:

  • Reinforcement learning (RL) in robotics raises safety and predictability concerns.
  • Defining accurate reward functions for complex tasks is challenging and prone to exploitation.
  • Existing methods lack formal guarantees for robot behavior.

Purpose of the Study:

  • To develop a formal methods approach for reinforcement learning in robotics.
  • To integrate high-level task specifications with domain-specific knowledge.
  • To ensure the safety and predictability of learned robot control policies.

Main Methods:

  • A predicate temporal logic tailored for robotic tasks.
  • An automaton-guided, safe reinforcement learning algorithm.
  • Control barrier functions for safety guarantees.

Main Results:

  • A formal specification language integrating task specifications and domain knowledge.
  • An interpretable reward generation process.
  • Guaranteed satisfaction of critical safety specifications.
  • Demonstration on a robotic cooking task.

Conclusions:

  • The proposed framework enhances the safety and predictability of reinforcement learning in robotics.
  • Formal methods can effectively guide policy generation and ensure critical safety constraints.
  • This approach offers a robust solution for complex robotic tasks requiring safety guarantees.