Interpreting Tactical Decision-making in Transformer-based Agents

Koen Boeckx; Xavier Neyt

Interpreting Tactical Decision-making in Transformer-based Agents

Publikation: Beitrag in Buch/Bericht/Konferenzband › Konferenzbeitrag › Begutachtung

7 Downloads (Pure)

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’s decision-making
process, specifically by visualizing which parts of the battlefield the network pays attention to when selecting an action. This

Originalsprache	Englisch
Titel	Proceedings of the 1st International Conference on Big Data & Applications
Untertitel	BDAA 2025
Redakteure/-innen	Sergey Y. Yurish
Erscheinungsort	2025
Herausgeber (Verlag)	International Frequency Sensor Association (IFSA) Publishing
Seiten	51-55
Seitenumfang	5
ISBN (elektronisch)	978-84-09-78845-3
Publikationsstatus	Veröffentlicht - 25 Nov. 2025
Veranstaltung	1st International Conference on Big Data Analytics and Applications - Austria Trend Hotel Congress Innsbruck, Innsbruck, Österreich Dauer: 25 Nov. 2025 → 27 Nov. 2025 Konferenznummer: 1 https://bdaa-conference.com/

Konferenz

Konferenz	1st International Conference on Big Data Analytics and Applications
Kurztitel	BDAA 2025
Land/Gebiet	Österreich
Ort	Innsbruck
Zeitraum	25/11/25 → 27/11/25
Internetadresse	https://bdaa-conference.com/

Zugriff auf Dokument

18_Paper_for_BDAA_2025Eingereichtes Manuskript, 1,43 MBLizenz: Nicht angegeben

CUGS: Intelligent Combat Unmanned Ground Systems (iCUGS)
Gallant, J. (Leitende(r) Forscher/-in), De cubber, G. (Leitende(r) Forscher/-in), Neyt, X. (Leitende(r) Forscher/-in), Le Flécher, E. (Leitende(r) Forscher/-in), Maroulis, E. (Forschende), Boeckx, K. (Forschende), Vanvolsem, P. (Forschende), Ndindabahizi, I. (Forschende) & Miranda Vicario, A. (Forschende)
1/04/23 → 1/10/26
Projekt: Forschung › EDA

Interpreting Tactical Decision-Making in Transformer-Based Agents
Boeckx, K. (Redner) & Neyt, X. (Co-author)
25 Nov. 2025
Aktivität: Gespräch oder Vortrag › Vortrag

Dieses zitieren

@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. in SY Yurish (Hrsg.), Proceedings of the 1st International Conference on Big Data & Applications: BDAA 2025., 18, International Frequency Sensor Association (IFSA) Publishing, 2025, S. 51-55, 1st International Conference on Big Data Analytics and Applications, Innsbruck, Österreich, 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. Hrsg. / Sergey Y. Yurish. 2025: International Frequency Sensor Association (IFSA) Publishing, 2025. S. 51-55 18.

Publikation: Beitrag in Buch/Bericht/Konferenzband › Konferenzbeitrag › Begutachtung

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

Abstract

Konferenz

Zugriff auf Dokument

Fingerprint

Projekte

CUGS: Intelligent Combat Unmanned Ground Systems (iCUGS)

Aktivitäten

Interpreting Tactical Decision-Making in Transformer-Based Agents

Dieses zitieren