BALANCING OF PERSONAL AND GROUP GOALS FOR AGENTS USING MULTI-AGENT REINFORCEMENT LEARNING

Simple item page
dc.contributor.authorZhabinets, Maxim
dc.date.accessioned2022-06-30T10:23:21Z
dc.date.available2022-06-30T10:23:21Z
dc.date.issued2022-04
dc.description.abstractThe number of AI agents in the world is increasing every day and they will need to interact with each other. It is in humanity’s best interest to teach these agents to respect the goals of others and live in harmony. In this study, we try to balance the personal and group goals of agents in social dilemma scenarios using the Proximal Policy Optimisation algorithm for both a decentralized learning approach and a centralized learning approach. After this, we compare the results of both approaches and point out their strong and weak points. We also test the impact of using an inequity-averse penalty that penalizes policies resulting in unequal rewards for agents in both decentralized and centralized learning. We briefly describe the history of multi-agent learning. We then look at the latest achievements in the application of centralized and decentralized multi-agent learning approaches, focusing on methods of balancing agents’ personal preferences with group goals. Next, the thesis describes the environments and methods used in this study. Then we describe the details of the performed experiments and discuss the results. We show that both centralized and decentralized learning approaches have their advantages and discuss them. We also show that inequity averse penalty is an efficient technique for balancing of the agents reward in social dilemma environments.en_US
dc.identifier.citationZhabinets, M. (2022). BALANCING OF PERSONAL AND GROUP GOALS FOR AGENTS USING MULTI-AGENT REINFORCEMENT LEARNING (Unpublished master's thesis). Nazarbayev University, Nur-Sultan, Kazakhstanen_US
dc.identifier.urihttp://nur.nu.edu.kz/handle/123456789/6357
dc.language.isoenen_US
dc.publisherNazarbayev University School of Engineering and Digital Sciencesen_US
dc.rightsAttribution-NonCommercial-ShareAlike 3.0 United States*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/3.0/us/*
dc.subjectResearch Subject Categories::TECHNOLOGYen_US
dc.subjectType of access: Open Accessen_US
dc.subjectProximal Policy Optimisation algorithmen_US
dc.subjectAIen_US
dc.subjectartificial intelligenceen_US
dc.subjectMulti-Agent Reinforcement Learningen_US
dc.subjectdecentralized learningen_US
dc.subjectReinforcement Learningen_US
dc.titleBALANCING OF PERSONAL AND GROUP GOALS FOR AGENTS USING MULTI-AGENT REINFORCEMENT LEARNINGen_US
dc.typeMaster's thesisen_US
workflow.import.sourcescience

Files

Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
Thesis - Maxim Zhabinets.pdf
Size:
1.36 MB
Format:
Adobe Portable Document Format
Description:
Thesis
Download
No Thumbnail Available
Name:
Presentation - Maxim Zhabinets.pptx
Size:
2.61 MB
Format:
Microsoft Powerpoint XML
Description:
Presentation
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
6.28 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

02. Master's Thesis