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

Decision Making: P-value Method

Decision Making: P-value Method

The process of hypothesis testing based on the P-value method includes calculating the P- value using the sample data and interpreting it.
First, a specific claim about the population parameter is proposed. The claim is based on the research question and is stated in a simple form. Further, an opposing statement to the claim is also stated. These statements can act as null and alternative hypotheses: a null hypothesis would be a neutral statement while the alternative hypothesis can...

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:

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,...

Improving Translational Accuracy

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...

Improving Translational Accuracy

Improving Translational Accuracy

Rolling Resistance: Problem Solving

Rolling Resistance: Problem Solving

Rolling resistance, also known as rolling friction, is the force that resists the motion of a rolling object, such as a wheel, tire, or ball, when it moves over a surface. It is caused by the deformation of the object and the surface in contact with each other, as well as other factors like internal friction, hysteresis, and energy losses within the materials. Rolling resistance opposes the object's motion, requiring additional energy to overcome it and maintain movement. In practical...

You might also read

Related Articles

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

Sort by

Same author

Nonlinear Bayesian Filtering With Natural Gradient Gaussian Approximation.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

On the Equilibrium Between Feasible Zone and Uncertain Model in Safe Exploration.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

Immune Predictors of Radiotherapy Outcomes in Cervical Cancer.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

Same author

Quantitative Representation of Autonomous Driving Scenario Difficulty Based on Adversarial Policy Search.

Research (Washington, D.C.)·2025

Same author

The timing of using IVIG for neonatal ABO hemolytic disease.

BMC pediatrics·2025

Same author

Feasible Policy Iteration With Guaranteed Safe Exploration.

IEEE transactions on cybernetics·2025

Search research articles

Related Experiment Video

Updated: Jan 18, 2026

Operant Protocols for Assessing the Cost-benefit Analysis During Reinforced Decision Making by Rodents

Operant Protocols for Assessing the Cost-benefit Analysis During Reinforced Decision Making by Rodents

Published on: September 10, 2018

Bicriteria Policy Optimization for High-Accuracy Reinforcement Learning.

Guojian Zhan, Xiangteng Zhang, Feihong Zhang

IEEE Transactions on Neural Networks and Learning Systems

|September 9, 2025

Summary

This summary is machine-generated.

This study introduces bicriteria policy optimization (BPO) for reinforcement learning (RL). BPO uses demonstration trajectories to improve policy approximation accuracy in complex control tasks, enhancing performance over standard methods.

More Related Videos

Pavlovian Conditioned Approach Training in Rats

Pavlovian Conditioned Approach Training in Rats

Published on: February 4, 2016

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Related Experiment Videos

Last Updated: Jan 18, 2026

Operant Protocols for Assessing the Cost-benefit Analysis During Reinforced Decision Making by Rodents

Operant Protocols for Assessing the Cost-benefit Analysis During Reinforced Decision Making by Rodents

Published on: September 10, 2018

Pavlovian Conditioned Approach Training in Rats

Pavlovian Conditioned Approach Training in Rats

Published on: February 4, 2016

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Area of Science:

Robotics and Control Systems
Artificial Intelligence
Machine Learning

Background:

Reinforcement learning (RL) approximates optimal policies using neural networks (NNs) for optimal control problems (OCPs).
Policy approximation accuracy is often limited in complex tasks due to rugged and flat value function landscapes, hindering convergence.
Existing methods struggle with satisfactory control performance compared to online optimal controllers.

Purpose of the Study:

To develop a novel algorithm, bicriteria policy optimization (BPO), to enhance policy approximation accuracy in RL.
To address the limitations of standard RL by incorporating optimal demonstration trajectories.
To improve control performance in complex tasks by guiding policy search at the gradient level.

Main Methods:

BPO formulates a bicriteria optimal control problem (OCP) with two objectives: standard reward signals and alignment with demonstration trajectories.
Introduced two co-state variables and two Hamiltonians to preserve minimum values for both objectives.
Developed a minimax optimization problem to resolve gradient conflicts, resulting in a 'harmonic gradient' for policy updates.
Simplified the optimization into a single-loop maximization problem via linear programming with convex trust region constraints.

Main Results:

The bicriteria OCP formulation and harmonic gradient approach effectively guide policy search.
The algorithm successfully minimizes conflicts between the two homomorphic objectives.
Experimental tests on linear and nonlinear control tasks demonstrated significant accuracy improvements in the policy network.

Conclusions:

BPO algorithm enhances the accuracy of policy approximation in reinforcement learning.
Leveraging demonstration trajectories provides a powerful mechanism for improving control performance.
The proposed method offers a computationally efficient and effective solution for complex control problems.