Interpreting Tactical Decision-making in Transformer-based Agents

Koen Boeckx; Xavier Neyt

Interpreting Tactical Decision-making in Transformer-based Agents

Résultats de recherche: Chapitre dans un livre, un rapport, des actes de conférences › Contribution à une conférence › Revue par des pairs

7 Téléchargements (Pure)

Résumé

The development of autonomous agents capable of sophisticated strategic decision-making in complex
environments is a central goal of artificial intelligence. This paper proposes a framework for discovering and interpreting
strategies in a simulated grid-world battlefield environment. We leverage the AlphaZero algorithm, a powerful reinforcement
learning method that combines Monte Carlo Tree Search (MCTS) with deep neural networks, to train agents. Crucially, the
neural network component incorporates a Transformer architecture. The primary contribution of this work lies in the proposed
methodology to utilize the self-attention mechanisms within the Transformer to gain insights into the agent’s decision-making
process, specifically by visualizing which parts of the battlefield the network pays attention to when selecting an action. This

langue originale	Anglais
titre	Proceedings of the 1st International Conference on Big Data & Applications
Sous-titre	BDAA 2025
rédacteurs en chef	Sergey Y. Yurish
Lieu de publication	2025
Editeur	International Frequency Sensor Association (IFSA) Publishing
Pages	51-55
Nombre de pages	5
ISBN (Electronique)	978-84-09-78845-3
état	Publié - 25 nov. 2025
Evénement	1st International Conference on Big Data Analytics and Applications - Austria Trend Hotel Congress Innsbruck, Innsbruck, Autriche Durée: 25 nov. 2025 → 27 nov. 2025 Numéro de conférence: 1 https://bdaa-conference.com/

Une conférence

Une conférence	1st International Conference on Big Data Analytics and Applications
Titre abrégé	BDAA 2025
Pays/Territoire	Autriche
La ville	Innsbruck
période	25/11/25 → 27/11/25
Adresse Internet	https://bdaa-conference.com/

Accès au document

18_Paper_for_BDAA_2025manuscrit soumis, 1,43 MBLicense: Non spécifié

CUGS: Intelligent Combat Unmanned Ground Systems (iCUGS)
Gallant, J. (Promoteur), De cubber, G. (Promoteur), Neyt, X. (Promoteur), Le Flécher, E. (Promoteur), Maroulis, E. (Chercheur), Boeckx, K. (Chercheur), Vanvolsem, P. (Chercheur), Ndindabahizi, I. (Chercheur) & Miranda Vicario, A. (Chercheur)
1/04/23 → 1/10/26
Projet: Recherche › AED

Interpreting Tactical Decision-Making in Transformer-Based Agents
Boeckx, K. (Orateur) & Neyt, X. (Co-auteur)
25 nov. 2025
Activité: Conférence ou présentation › Présentation orale à caractère scientifique

Contient cette citation

@inproceedings{42a912bb56c44bdf934c1674e97cfe25,

title = "Interpreting Tactical Decision-making in Transformer-based Agents",

abstract = "The development of autonomous agents capable of sophisticated strategic decision-making in complex environments is a central goal of artificial intelligence. This paper proposes a framework for discovering and interpreting strategies in a simulated grid-world battlefield environment. We leverage the AlphaZero algorithm, a powerful reinforcement learning method that combines Monte Carlo Tree Search (MCTS) with deep neural networks, to train agents. Crucially, the neural network component incorporates a Transformer architecture. The primary contribution of this work lies in the proposed methodology to utilize the self-attention mechanisms within the Transformer to gain insights into the agent{\textquoteright}s decision-making process, specifically by visualizing which parts of the battlefield the network pays attention to when selecting an action. This ",

author = "Koen Boeckx and Xavier Neyt",

year = "2025",

month = nov,

day = "25",

language = "English",

pages = "51--55",

editor = "Yurish, \{Sergey Y.\}",

booktitle = "Proceedings of the 1st International Conference on Big Data \& Applications",

publisher = "International Frequency Sensor Association (IFSA) Publishing",

note = "1st International Conference on Big Data Analytics and Applications, BDAA 2025 ; Conference date: 25-11-2025 Through 27-11-2025",

url = "https://bdaa-conference.com/",

}

Boeckx, K & Neyt, X 2025, Interpreting Tactical Decision-making in Transformer-based Agents. Dans SY Yurish (Ed.), Proceedings of the 1st International Conference on Big Data & Applications: BDAA 2025., 18, International Frequency Sensor Association (IFSA) Publishing, 2025, p. 51-55, 1st International Conference on Big Data Analytics and Applications, Innsbruck, Autriche, 25/11/25.

Interpreting Tactical Decision-making in Transformer-based Agents. / Boeckx, Koen ; Neyt, Xavier.
Proceedings of the 1st International Conference on Big Data & Applications: BDAA 2025. Ed. / Sergey Y. Yurish. 2025: International Frequency Sensor Association (IFSA) Publishing, 2025. p. 51-55 18.

Résultats de recherche: Chapitre dans un livre, un rapport, des actes de conférences › Contribution à une conférence › Revue par des pairs

TY - GEN

T1 - Interpreting Tactical Decision-making in Transformer-based Agents

AU - Boeckx, Koen

AU - Neyt, Xavier

N1 - Conference code: 1

PY - 2025/11/25

Y1 - 2025/11/25

N2 - The development of autonomous agents capable of sophisticated strategic decision-making in complex environments is a central goal of artificial intelligence. This paper proposes a framework for discovering and interpreting strategies in a simulated grid-world battlefield environment. We leverage the AlphaZero algorithm, a powerful reinforcement learning method that combines Monte Carlo Tree Search (MCTS) with deep neural networks, to train agents. Crucially, the neural network component incorporates a Transformer architecture. The primary contribution of this work lies in the proposed methodology to utilize the self-attention mechanisms within the Transformer to gain insights into the agent’s decision-making process, specifically by visualizing which parts of the battlefield the network pays attention to when selecting an action. This

AB - The development of autonomous agents capable of sophisticated strategic decision-making in complex environments is a central goal of artificial intelligence. This paper proposes a framework for discovering and interpreting strategies in a simulated grid-world battlefield environment. We leverage the AlphaZero algorithm, a powerful reinforcement learning method that combines Monte Carlo Tree Search (MCTS) with deep neural networks, to train agents. Crucially, the neural network component incorporates a Transformer architecture. The primary contribution of this work lies in the proposed methodology to utilize the self-attention mechanisms within the Transformer to gain insights into the agent’s decision-making process, specifically by visualizing which parts of the battlefield the network pays attention to when selecting an action. This

M3 - Conference contribution

SP - 51

EP - 55

BT - Proceedings of the 1st International Conference on Big Data & Applications

A2 - Yurish, Sergey Y.

PB - International Frequency Sensor Association (IFSA) Publishing

CY - 2025

T2 - 1st International Conference on Big Data Analytics and Applications

Y2 - 25 November 2025 through 27 November 2025

ER -

Interpreting Tactical Decision-making in Transformer-based Agents

Résumé

Une conférence

Accès au document

Empreinte digitale

Projets

CUGS: Intelligent Combat Unmanned Ground Systems (iCUGS)

Activités

Interpreting Tactical Decision-Making in Transformer-Based Agents

Contient cette citation