‘The six pac-men' : exploring the strength of advice provision and the impact of an adversarial advisor in reinforcement learning

Reinforcement learning in multi-agent scenarios is gaining popularity in recent times, with the student-teacher framework claiming its efficiency in the context of advice provision. The research in this paper describes a single-student-multi-teacher setting of a game environment. A new game titled...

Full description

Saved in:
Bibliographic Details
Main Author: Arun, Rakshitha
Other Authors: Zinovi Rabinovich
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2021
Subjects:
Online Access:https://hdl.handle.net/10356/148063
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-148063
record_format dspace
spelling sg-ntu-dr.10356-1480632021-04-22T11:49:58Z ‘The six pac-men' : exploring the strength of advice provision and the impact of an adversarial advisor in reinforcement learning Arun, Rakshitha Zinovi Rabinovich School of Computer Science and Engineering Computational Intelligence Lab zinovi@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Reinforcement learning in multi-agent scenarios is gaining popularity in recent times, with the student-teacher framework claiming its efficiency in the context of advice provision. The research in this paper describes a single-student-multi-teacher setting of a game environment. A new game titled ‘Pac-Man Lite’ has been implemented for the purpose of experimentation. This environment is used to study advice provision between the student and teacher agents. First, the ability of the student agent to aggregate advice from multiple teachers with partial visibility of the environment is studied. Subsequently, an attacker in the form of an adversarial teacher advisor with a full view of the environment is introduced into the setting, whose goal is slightly different from that of the existing agents. The significant impact that adversarial advice can have on the performance of an agent serves as the major motivation behind this project. The research studies the effectiveness of adversarial advice in negatively influencing the performance of the student agent from the adversarial teacher agent’s perspective. The results indicate that the student agent is able to aggregate advice and extract value from relevant advisors in the presence of multiple sources. The results also indicate the success of the adversarial agent in negatively impacting the performance of the student agent by participating in advice provision. In addition to adding to existing research, this work has also set the ground for future research in multiple directions. Bachelor of Engineering (Computer Science) 2021-04-22T11:49:57Z 2021-04-22T11:49:57Z 2021 Final Year Project (FYP) Arun, R. (2021). ‘The six pac-men' : exploring the strength of advice provision and the impact of an adversarial advisor in reinforcement learning. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/148063 https://hdl.handle.net/10356/148063 en SCSE20-0482 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
Arun, Rakshitha
‘The six pac-men' : exploring the strength of advice provision and the impact of an adversarial advisor in reinforcement learning
description Reinforcement learning in multi-agent scenarios is gaining popularity in recent times, with the student-teacher framework claiming its efficiency in the context of advice provision. The research in this paper describes a single-student-multi-teacher setting of a game environment. A new game titled ‘Pac-Man Lite’ has been implemented for the purpose of experimentation. This environment is used to study advice provision between the student and teacher agents. First, the ability of the student agent to aggregate advice from multiple teachers with partial visibility of the environment is studied. Subsequently, an attacker in the form of an adversarial teacher advisor with a full view of the environment is introduced into the setting, whose goal is slightly different from that of the existing agents. The significant impact that adversarial advice can have on the performance of an agent serves as the major motivation behind this project. The research studies the effectiveness of adversarial advice in negatively influencing the performance of the student agent from the adversarial teacher agent’s perspective. The results indicate that the student agent is able to aggregate advice and extract value from relevant advisors in the presence of multiple sources. The results also indicate the success of the adversarial agent in negatively impacting the performance of the student agent by participating in advice provision. In addition to adding to existing research, this work has also set the ground for future research in multiple directions.
author2 Zinovi Rabinovich
author_facet Zinovi Rabinovich
Arun, Rakshitha
format Final Year Project
author Arun, Rakshitha
author_sort Arun, Rakshitha
title ‘The six pac-men' : exploring the strength of advice provision and the impact of an adversarial advisor in reinforcement learning
title_short ‘The six pac-men' : exploring the strength of advice provision and the impact of an adversarial advisor in reinforcement learning
title_full ‘The six pac-men' : exploring the strength of advice provision and the impact of an adversarial advisor in reinforcement learning
title_fullStr ‘The six pac-men' : exploring the strength of advice provision and the impact of an adversarial advisor in reinforcement learning
title_full_unstemmed ‘The six pac-men' : exploring the strength of advice provision and the impact of an adversarial advisor in reinforcement learning
title_sort ‘the six pac-men' : exploring the strength of advice provision and the impact of an adversarial advisor in reinforcement learning
publisher Nanyang Technological University
publishDate 2021
url https://hdl.handle.net/10356/148063
_version_ 1698713707172855808