Multi-Agent System for Emulating Personality Traits Using Deep Reinforcement Learning

Conventional personality assessment methods depend on subjective input, while game-based AI predictive methods offer a dynamic and objective framework. However, training these models requires large and labeled datasets, which are challenging to obtain from real players with diverse personality trait...

Full description

Saved in:
Bibliographic Details
Main Authors: Georgios Liapis, Ioannis Vlahavas
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/14/24/12068
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850239822081294336
author Georgios Liapis
Ioannis Vlahavas
author_facet Georgios Liapis
Ioannis Vlahavas
author_sort Georgios Liapis
collection DOAJ
description Conventional personality assessment methods depend on subjective input, while game-based AI predictive methods offer a dynamic and objective framework. However, training these models requires large and labeled datasets, which are challenging to obtain from real players with diverse personality traits. In this paper, we propose a multi-agent system using Deep Reinforcement Learning in a game environment to generate the necessary labeled data. Each agent is trained with custom reward functions based on the HiDAC system that encourages trait-aligned behaviors to emulate specific personality traits based on the OCEAN personality trait model. The Multi-Agent Posthumous Credit Assignment (MA-POCA) algorithm facilitates continuous learning, allowing agents to emulate behaviors through self-play. The resulting gameplay data provide diverse, high-quality samples. This approach allows for robust individual and team assessments, as agent interactions reveal the impact of personality traits on team dynamics and performance. Ultimately, this methodology provides a scalable, unbiased methodology for human personality evaluation in various settings, establishing new standards for data-driven assessment methods.
format Article
id doaj-art-2cf18d6a2de24913b85c6a4e3fcbd18c
institution OA Journals
issn 2076-3417
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-2cf18d6a2de24913b85c6a4e3fcbd18c2025-08-20T02:01:03ZengMDPI AGApplied Sciences2076-34172024-12-0114241206810.3390/app142412068Multi-Agent System for Emulating Personality Traits Using Deep Reinforcement LearningGeorgios Liapis0Ioannis Vlahavas1School of Informatics, Aristotle University of Thessaloniki, 541 24 Thessaloniki, GreeceSchool of Informatics, Aristotle University of Thessaloniki, 541 24 Thessaloniki, GreeceConventional personality assessment methods depend on subjective input, while game-based AI predictive methods offer a dynamic and objective framework. However, training these models requires large and labeled datasets, which are challenging to obtain from real players with diverse personality traits. In this paper, we propose a multi-agent system using Deep Reinforcement Learning in a game environment to generate the necessary labeled data. Each agent is trained with custom reward functions based on the HiDAC system that encourages trait-aligned behaviors to emulate specific personality traits based on the OCEAN personality trait model. The Multi-Agent Posthumous Credit Assignment (MA-POCA) algorithm facilitates continuous learning, allowing agents to emulate behaviors through self-play. The resulting gameplay data provide diverse, high-quality samples. This approach allows for robust individual and team assessments, as agent interactions reveal the impact of personality traits on team dynamics and performance. Ultimately, this methodology provides a scalable, unbiased methodology for human personality evaluation in various settings, establishing new standards for data-driven assessment methods.https://www.mdpi.com/2076-3417/14/24/12068machine learningserious gamespersonality assessmentmulti-agent
spellingShingle Georgios Liapis
Ioannis Vlahavas
Multi-Agent System for Emulating Personality Traits Using Deep Reinforcement Learning
Applied Sciences
machine learning
serious games
personality assessment
multi-agent
title Multi-Agent System for Emulating Personality Traits Using Deep Reinforcement Learning
title_full Multi-Agent System for Emulating Personality Traits Using Deep Reinforcement Learning
title_fullStr Multi-Agent System for Emulating Personality Traits Using Deep Reinforcement Learning
title_full_unstemmed Multi-Agent System for Emulating Personality Traits Using Deep Reinforcement Learning
title_short Multi-Agent System for Emulating Personality Traits Using Deep Reinforcement Learning
title_sort multi agent system for emulating personality traits using deep reinforcement learning
topic machine learning
serious games
personality assessment
multi-agent
url https://www.mdpi.com/2076-3417/14/24/12068
work_keys_str_mv AT georgiosliapis multiagentsystemforemulatingpersonalitytraitsusingdeepreinforcementlearning
AT ioannisvlahavas multiagentsystemforemulatingpersonalitytraitsusingdeepreinforcementlearning