Skip to main navigation
Skip to search
Skip to main content
TU Delft Research Portal Home
Help & FAQ
Home
Research units
Researchers
Research output
Datasets
Projects
Press/Media
Prizes
Activities
Search by expertise, name or affiliation
Genetic programming methods for reinforcement learning
R Babuska
Learning & Autonomous Control
Research output
:
Contribution to conference
›
Abstract
›
Scientific
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Genetic programming methods for reinforcement learning'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
INIS
genetics
100%
programming
100%
learning
100%
algorithms
60%
control
40%
mapping
40%
values
40%
neural networks
40%
dynamics
20%
box models
20%
expansion
20%
nonlinear problems
20%
policy
20%
genes
20%
errors
20%
tuning
20%
decision making
20%
Computer Science
Reinforcement Learning
100%
Programming Method
100%
Genetic Programming
100%
Networking Function
20%
Dynamic Decision
20%
Deep Neural Network
20%
non linear control
20%
And-States
20%
Process Model
20%
Algorithms
20%
Reproducibility
20%
Mathematics
Algorithm
100%
Control Problems
66%
Function Value
66%
Deep Neural Network
33%
Variables
33%
Trial and error
33%
Nonlinear Control
33%
Analytic Expression
33%
Engineering
Approximators
60%
Symbolics
40%
Mapping
40%
Value Function
40%
Nodes
20%
Models
20%
Error
20%
Black-Box Model
20%
Network Function
20%
Fields
20%
Illustrates
20%
Chemical Engineering
Neural Network
20%
Deep Neural Network
20%
Neuroscience
Decision-Making
20%