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

Regression Toward the Mean01:52

Regression Toward the Mean

6.9K
Regression toward the mean (“RTM”) is a phenomenon in which extremely high or low values—for example, and individual’s blood pressure at a particular moment—appear closer to a group’s average upon remeasuring. Although this statistical peculiarity is the result of random error and chance, it has been problematic across various medical, scientific, financial and psychological applications. In particular, RTM, if not taken into account, can interfere when...
6.9K
Analysis of Population Pharmacokinetic Data01:12

Analysis of Population Pharmacokinetic Data

682
Analysis of population pharmacokinetic data involves studying the behavior of drugs within diverse populations to understand their pharmacokinetic parameters. Traditional pharmacokinetic methods typically involve collecting samples from a few individuals and estimating these parameters. While these methods are commonly used, they have limitations in capturing the variability in drug response among individuals or heterogeneous populations. Population pharmacokinetics is employed to address these...
682
Mechanistic Models: Compartment Models in Individual and Population Analysis01:23

Mechanistic Models: Compartment Models in Individual and Population Analysis

250
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
250
Strategies for Assessing and Addressing Confounding01:25

Strategies for Assessing and Addressing Confounding

365
Confounding is a critical issue in epidemiological studies, often leading to misleading conclusions about associations between exposures and outcomes. It occurs when the relationship between the exposure and the outcome is mixed with the effects of other factors that influence the outcome. Given that, addressing confounding is of high importance for drawing accurate inferences in research.
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
365
Analysis Methods of Pharmacokinetic Data: Model and Model-Independent Approaches01:14

Analysis Methods of Pharmacokinetic Data: Model and Model-Independent Approaches

495
Drug disposition in the body is a complex process and can be studied using two major approaches: the model and the model-independent approaches.
The model approach uses mathematical models to describe changes in drug concentration over time. Pharmacokinetic models help characterize drug behavior in patients, predict drug concentration in the body fluids, calculate optimum dosage regimens, and evaluate the risk of toxicity. However, ensuring that the model fits the experimental data accurately...
495
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

292
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...
292

You might also read

Related Articles

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

Sort by
Same author

Corrigendum to "Enhanced fluorescence imaging guided photodynamic therapy of sinoporphyrin sodium loaded graphene oxide" [Biomaterials 42 (2015) 16442].

Biomaterials·2026
Same author

Functional Characterisation of NF-YCs in True Leaf Biomass Accumulation.

Plants (Basel, Switzerland)·2026
Same author

Sex- and age-dependent physiological adaptation of captive père david's deer revealed by multi-omics analysis.

BMC genomics·2026
Same author

Correction to "Triphase Interface Synthesis of Plasmonic Gold Bellflowers as Near-Infrared Light Mediated Acoustic and Thermal Theranostics".

Journal of the American Chemical Society·2026
Same author

Instance-dependent Early Stopping for Adaptive Data Pruning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Genome-Wide Analysis of the <i>KNOX</i> Gene Family in <i>Malus sieversii</i>.

Plants (Basel, Switzerland)·2026

Related Experiment Video

Updated: Jan 19, 2026

Development of an Individual-Tree Basal Area Increment Model using a Linear Mixed-Effects Approach
04:35

Development of an Individual-Tree Basal Area Increment Model using a Linear Mixed-Effects Approach

Published on: July 3, 2020

3.7K

Analysis and improvement of policy gradient estimation.

Tingting Zhao1, Hirotaka Hachiya, Gang Niu

  • 1Tokyo Institute of Technology, 2-12-1-W8-74, O-okayama, Tokyo, 152-8552, Japan. tingting@sg.cs.titech.ac.jp

Neural Networks : the Official Journal of the International Neural Network Society
|October 25, 2011
PubMed
Summary
This summary is machine-generated.

Policy gradient methods in reinforcement learning are unstable. This study improves policy gradients with parameter-based exploration (PGPE), showing it has lower gradient variance than REINFORCE, especially with an optimal baseline.

More Related Videos

Probing the Limits of Egg Recognition Using Egg Rejection Experiments Along Phenotypic Gradients
07:34

Probing the Limits of Egg Recognition Using Egg Rejection Experiments Along Phenotypic Gradients

Published on: August 22, 2018

8.6K
A Novel Bayesian Change-point Algorithm for Genome-wide Analysis of Diverse ChIPseq Data Types
12:39

A Novel Bayesian Change-point Algorithm for Genome-wide Analysis of Diverse ChIPseq Data Types

Published on: December 10, 2012

11.7K

Related Experiment Videos

Last Updated: Jan 19, 2026

Development of an Individual-Tree Basal Area Increment Model using a Linear Mixed-Effects Approach
04:35

Development of an Individual-Tree Basal Area Increment Model using a Linear Mixed-Effects Approach

Published on: July 3, 2020

3.7K
Probing the Limits of Egg Recognition Using Egg Rejection Experiments Along Phenotypic Gradients
07:34

Probing the Limits of Egg Recognition Using Egg Rejection Experiments Along Phenotypic Gradients

Published on: August 22, 2018

8.6K
A Novel Bayesian Change-point Algorithm for Genome-wide Analysis of Diverse ChIPseq Data Types
12:39

A Novel Bayesian Change-point Algorithm for Genome-wide Analysis of Diverse ChIPseq Data Types

Published on: December 10, 2012

11.7K

Area of Science:

  • Reinforcement Learning
  • Machine Learning
  • Artificial Intelligence

Background:

  • Policy gradient methods are model-free reinforcement learning algorithms.
  • These methods often suffer from unstable gradient estimates, limiting their effectiveness.
  • Policy Gradients with Parameter-based Exploration (PGPE) and REINFORCE are two prominent methods.

Purpose of the Study:

  • To analyze and enhance the stability of policy gradient methods.
  • To theoretically compare the gradient estimate variance of PGPE and REINFORCE.
  • To introduce an optimal baseline for PGPE to further reduce variance.

Main Methods:

  • Theoretical analysis of gradient estimate variance.
  • Derivation of the optimal baseline for PGPE.
  • Experimental validation of the improved PGPE method.

Main Results:

  • Proved that PGPE has smaller gradient estimate variance than REINFORCE under mild assumptions.
  • Derived the optimal baseline for PGPE, further reducing variance.
  • Theoretically demonstrated PGPE with an optimal baseline is superior to REINFORCE with an optimal baseline regarding gradient variance.

Conclusions:

  • The improved PGPE method offers enhanced stability for policy gradient reinforcement learning.
  • PGPE with an optimal baseline presents a more stable and preferable alternative to REINFORCE.
  • Experimental results confirm the practical utility of the enhanced PGPE method.