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

• Alexandre M. M. Santos UFC
• Halisson R. Rodrigues UFC
• Romulo F. Férrer Filho UFC
• Yuri L. B. Nogueira UFC
• Creto A. Vidal UFC
• Joaquim B. Cavalcante-Neto UFC
• Artur O. R. Franco UFC
• Paulo B. S. Serafim Gran Sasso Science Institute

Resumo

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.

Palavras-chave: Deep Reinforcement Learning, Diversity Hypothesis, Domain Randomization, Explainable Artificial intelligence, Game Agent, Generalization, Saliency Maps