Implementation of reinforcement learning using neural network

Implementation of reinforcement learning using neural network

Reinforcement learning is an area of machine learning solving the problems that how to take actions to get optimal goals in some certain environment. One kind of reinforcement learning algorithm—Q-learning integrated with neural network is proposed in this project to improve the performance of reinf...

Full description

Saved in:
Bibliographic Details
Main Author: Chang, Zhanhua
Other Authors: Er Meng Joo
Format: Final Year Project
Language:English
Published: 2015
Subjects:
DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation
Online Access:http://hdl.handle.net/10356/64250
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-64250
record_format dspace
spelling sg-ntu-dr.10356-642502023-07-07T16:31:38Z Implementation of reinforcement learning using neural network Chang, Zhanhua Er Meng Joo School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation Reinforcement learning is an area of machine learning solving the problems that how to take actions to get optimal goals in some certain environment. One kind of reinforcement learning algorithm—Q-learning integrated with neural network is proposed in this project to improve the performance of reinforcement learning algorithm. This paper will present the implementation of the Q-learning with backpropagation neural network. The programming algorithm and its functions are discussed in details. The performance of the algorithms and its influencing factors are tested in the mountain car problem benchmark. The results indicate that reinforcement learning using neural network is feasible and outperform with mass of data. A summary of the project and future work will also be provided in the end. Bachelor of Engineering 2015-05-25T07:43:30Z 2015-05-25T07:43:30Z 2015 2015 Final Year Project (FYP) http://hdl.handle.net/10356/64250 en Nanyang Technological University 42 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation
spellingShingle DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation
Chang, Zhanhua
Implementation of reinforcement learning using neural network
description Reinforcement learning is an area of machine learning solving the problems that how to take actions to get optimal goals in some certain environment. One kind of reinforcement learning algorithm—Q-learning integrated with neural network is proposed in this project to improve the performance of reinforcement learning algorithm. This paper will present the implementation of the Q-learning with backpropagation neural network. The programming algorithm and its functions are discussed in details. The performance of the algorithms and its influencing factors are tested in the mountain car problem benchmark. The results indicate that reinforcement learning using neural network is feasible and outperform with mass of data. A summary of the project and future work will also be provided in the end.
author2 Er Meng Joo
author_facet Er Meng Joo
Chang, Zhanhua
format Final Year Project
author Chang, Zhanhua
author_sort Chang, Zhanhua
title Implementation of reinforcement learning using neural network
title_short Implementation of reinforcement learning using neural network
title_full Implementation of reinforcement learning using neural network
title_fullStr Implementation of reinforcement learning using neural network
title_full_unstemmed Implementation of reinforcement learning using neural network
title_sort implementation of reinforcement learning using neural network
publishDate 2015
url http://hdl.handle.net/10356/64250
_version_ 1772827489713782784

Similar Items