Interpreting Tactical Decision-making in Transformer-based Agents

Koen Boeckx; Xavier Neyt

Interpreting Tactical Decision-making in Transformer-based Agents

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/Congresprocedure › Conferentiebijdrage › peer review

7 Downloads (Pure)

Samenvatting

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

Originele taal-2	Engels
Titel	Proceedings of the 1st International Conference on Big Data & Applications
Subtitel	BDAA 2025
Redacteuren	Sergey Y. Yurish
Plaats van productie	2025
Uitgeverij	International Frequency Sensor Association (IFSA) Publishing
Pagina's	51-55
Aantal pagina's	5
ISBN van elektronische versie	978-84-09-78845-3
Status	Gepubliceerd - 25 nov 2025
Evenement	1st International Conference on Big Data Analytics and Applications - Austria Trend Hotel Congress Innsbruck, Innsbruck, Oostenrijk Duur: 25 nov 2025 → 27 nov 2025 Congresnummer: 1 https://bdaa-conference.com/

Congres

Congres	1st International Conference on Big Data Analytics and Applications
Verkorte titel	BDAA 2025
Land/Regio	Oostenrijk
Stad	Innsbruck
Periode	25/11/25 → 27/11/25
Internet adres	https://bdaa-conference.com/

Toegang tot document

18_Paper_for_BDAA_2025Ingediend manuscript, 1,43 MBLicentie: Onbepaald

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

Interpreting Tactical Decision-Making in Transformer-Based Agents
Boeckx, K. (Spreker) & Neyt, X. (Co-auteur)
25 nov 2025
Activiteit: Conferentie of presentatie › Mondelinge wetenschappelijke presentatie

Citeer dit

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

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/Congresprocedure › Conferentiebijdrage › peer review

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

Samenvatting

Congres

Toegang tot document

Vingerafdruk

Projecten

CUGS: Intelligent Combat Unmanned Ground Systems (iCUGS)

Activiteiten

Interpreting Tactical Decision-Making in Transformer-Based Agents

Citeer dit