Lying in pursuit evasion task with multi-agent reinforcement learning

Swarm behaviour in nature has long been an area of research, through which many algorithms have been developed and have found applications in modern problems. A particular research field of multi-agent systems, which are more general to swarms, focuses on using multi-agent reinforcement learning to...

Full description

Saved in:
Bibliographic Details
Main Author: Cheng, Damien Shiao Kiat
Other Authors: Zinovi Rabinovich
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2022
Subjects:
Online Access:https://hdl.handle.net/10356/157325
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-157325
record_format dspace
spelling sg-ntu-dr.10356-1573252022-05-18T06:09:21Z Lying in pursuit evasion task with multi-agent reinforcement learning Cheng, Damien Shiao Kiat Zinovi Rabinovich School of Computer Science and Engineering zinovi@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Swarm behaviour in nature has long been an area of research, through which many algorithms have been developed and have found applications in modern problems. A particular research field of multi-agent systems, which are more general to swarms, focuses on using multi-agent reinforcement learning to develop and learn policies of high performance. Communication between agents do exist within swarms and within multi-agent systems, and have been modelled during research. However, lying during communication is an area lacking in research. This project will investigate the effects of lying on a multi-agent system in a pursuit evasion task using multi-agent reinforcement learning to learn an optimal policy, and experiment with different network configurations and techniques such as dropout and layer normalisation.
 Bachelor of Engineering (Computer Science) 2022-05-18T06:09:20Z 2022-05-18T06:09:20Z 2022 Final Year Project (FYP) Cheng, D. S. K. (2022). Lying in pursuit evasion task with multi-agent reinforcement learning. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/157325 https://hdl.handle.net/10356/157325 en application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
spellingShingle Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Cheng, Damien Shiao Kiat
Lying in pursuit evasion task with multi-agent reinforcement learning
description Swarm behaviour in nature has long been an area of research, through which many algorithms have been developed and have found applications in modern problems. A particular research field of multi-agent systems, which are more general to swarms, focuses on using multi-agent reinforcement learning to develop and learn policies of high performance. Communication between agents do exist within swarms and within multi-agent systems, and have been modelled during research. However, lying during communication is an area lacking in research. This project will investigate the effects of lying on a multi-agent system in a pursuit evasion task using multi-agent reinforcement learning to learn an optimal policy, and experiment with different network configurations and techniques such as dropout and layer normalisation.

author2 Zinovi Rabinovich
author_facet Zinovi Rabinovich
Cheng, Damien Shiao Kiat
format Final Year Project
author Cheng, Damien Shiao Kiat
author_sort Cheng, Damien Shiao Kiat
title Lying in pursuit evasion task with multi-agent reinforcement learning
title_short Lying in pursuit evasion task with multi-agent reinforcement learning
title_full Lying in pursuit evasion task with multi-agent reinforcement learning
title_fullStr Lying in pursuit evasion task with multi-agent reinforcement learning
title_full_unstemmed Lying in pursuit evasion task with multi-agent reinforcement learning
title_sort lying in pursuit evasion task with multi-agent reinforcement learning
publisher Nanyang Technological University
publishDate 2022
url https://hdl.handle.net/10356/157325
_version_ 1734310235562049536