In this paper, we investigate the semantic clustering properties of deep reinforcement learning (DRL) for video games, enriching our understanding of the internal dynamics of DRL and advancing its interpretability. In this context, semantic clustering refers to the inherent capacity of neural networks to internally group video inputs based on semantic similarity. To achieve this, we propose a novel DRL architecture that integrates a semantic clustering module featuring both feature dimensionality reduction and online clustering. This module seamlessly integrates into the DRL training pipeline, addressing instability issues observed in previous t-SNE-based analysis methods and eliminating the necessity for extensive manual annotation of semantic analysis. Through experiments, we validate the effectiveness of the proposed module and the semantic clustering properties in DRL for video games. Additionally, based on these properties, we introduce new analytical methods to help understand the hierarchical structure of policies and the semantic distribution within the feature space.

翻译：本文研究了深度强化学习（DRL）在视频游戏中的语义聚类特性，以深化对DRL内部动态的理解并提升其可解释性。在此语境下，语义聚类指神经网络基于语义相似性对视频输入进行内部分组的内在能力。为此，我们提出了一种新颖的DRL架构，该架构集成了一个兼具特征降维与在线聚类功能的语义聚类模块。该模块可无缝集成至DRL训练流程中，解决了以往基于t-SNE的分析方法中观察到的不稳定性问题，并消除了对语义分析进行大量人工标注的需求。通过实验，我们验证了所提模块的有效性以及DRL在视频游戏中的语义聚类特性。此外，基于这些特性，我们引入了新的分析方法，以助于理解策略的层次结构及特征空间内的语义分布。