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
Sample effficient deep reinforcement learning for control
Tim de Bruin
Learning & Autonomous Control
Research output
:
Thesis
›
Dissertation (TU Delft)
487
Downloads (Pure)
Overview
Fingerprint
Research output
(6)
Fingerprint
Dive into the research topics of 'Sample effficient deep reinforcement learning for control'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Computer Science
Deep Reinforcement Learning
100%
Reinforcement Learning
100%
Robot
60%
Legal Decision
40%
Procedures
40%
Algorithms
30%
Learning Process
30%
Deep Neural Network
20%
Representation Learning
20%
Robotics
20%
Neural Network
20%
Networking Function
10%
State Space
10%
Network Target
10%
Standards
10%
Data Diversity
10%
Learning Agent
10%
Training Objective
10%
Frequency Control
10%
Optimization Technique
10%
Function Approximation
10%
Mathematical Optimization
10%
INIS
control
100%
learning
100%
optimization
24%
data
24%
robots
20%
policy
17%
algorithms
17%
distribution
13%
neural networks
13%
space
13%
buffers
13%
utilities
13%
exploration
10%
performance
10%
hands
6%
mapping
6%
trains
6%
streams
6%
errors
6%
tuning
6%
sensitivity
3%
levels
3%
maps
3%
values
3%
prices
3%
simulation
3%
range
3%
speed
3%
compacts
3%
approximations
3%
frequency control
3%
reviews
3%
stability
3%
tools
3%
sensors
3%
humans
3%
environment
3%
size
3%
sampling
3%
Psychology
Reinforcement
100%
Training
46%
Neural Network
26%
Judgement
26%
Humans
6%
Trust
6%
Learning Algorithm
6%
Abilities
6%
Forgetting
6%
Tools
6%
Chemical Engineering
Reinforcement Learning
100%
Neural Network
13%
Deep Neural Network
13%
Material Science
Sensor
100%
Engineering
Network Function
6%
Target Network
6%
Additional Training
6%
Instantaneous Utility
6%