Unveiling the Key Features Influencing Game Agents with Different Levels of Robustness

XXII Brazilian Symposium on Computer Games and Digital Entertainment (SBGames)

Alexandre Magno Monteiro Santos¹   Halisson Rodrigo Rodrigues¹   Rômulo Freire Férrer Filho¹
Yuri Lenon Barbosa Nogueira¹   Creto Augusto Vidal¹   Joaquim Bento Cavalcante Neto¹
Artur de Oliveira da Rocha Franco¹   Paulo Bruno de Sousa Serafim²

¹Department of Computing (DC), Federal University of Ceará (UFC)
²Computer Science, Gran Sasso Science Institute (GSSI)

---

Page: [ACM]

Abstract

Training agents using Deep Reinforcement Learning methods is rapidly progressing in several fields and techniques like domain randomization have been demonstrated to improve the generalization ability of these agents. However, due to the black-box nature of the models, it is not easy to understand why an action was selected from a given input. Although prior research on Explainable Artificial Intelligence presents efforts to bridge this gap, is unclear what particular input features that contribute to a model’s generalizability. This work examines the main aspects that affect the behavior of game agents with varying robustness levels. By comparing specialized and generalized agents, we investigate what are the main differences and similarities present in these models when they select an action. To achieve this goal, we trained two agents with different robustness levels and applied Explainable Artificial Intelligence methods to highlight the key features on the input screen. We employed a mixed methods analysis, which provided important quantitative results on the agents’ performance as well as qualitative insights about their behavior. We are able to show that the visualization of generalized agents tends to be more interpretable since they concentrate on the game objects, whereas specialized agents are more spread along the whole input screen. This result constitutes an important step to understanding the behavior of game agents trained using Deep Reinforcement Learning with different training procedures.

BibTeX

Download

@InProceedings{santos2023unveiling,
  title = {Unveiling the Key Features Influencing Game Agents with Different Levels of Robustness},
  author  = {Santos, Alexandre Magno Monteiro and
    Rodrigues, Halisson Rodrigo and
    F\'{e}rrer Filho, R\^{o}mulo Freire and
    Nogueira, Yuri Lenon Barbosa and
    Vidal, Creto Augusto and
    Cavalcante-Neto, Joaquim Bento and
    Franco, Artur Oliveira Rocha and
    Serafim, Paulo Bruno Sousa},
  booktitle = {Proceedings of the XXII Brazilian Symposium on Computer Games and Digital Entertainment (SBGames)},
  pages = {86--95},
  year = {2023},
  doi = {10.1145/3631085.3631230}
}