Despite the impressive feats demonstrated by Reinforcement Learning (RL), these algorithms have seen little adoption in high-risk, real-world applications due to current difficulties in explaining RL agent actions and building user trust. We present Counterfactual Demonstrations for Explanation (CODEX), a method that incorporates semantic clustering, which can effectively summarize RL agent behavior in the state-action space. Experimentation on the MiniGrid and StarCraft II gaming environments reveals the semantic clusters retain temporal as well as entity information, which is reflected in the constructed summary of agent behavior. Furthermore, clustering the discrete+continuous game-state latent representations identifies the most crucial episodic events, demonstrating a relationship between the latent and semantic spaces. This work contributes to the growing body of work that strives to unlock the power of RL for widespread use by leveraging and extending techniques from Natural Language Processing.

通过语义聚类的方法，该研究提出了对强化学习（RL）代理行为进行总结的方法CODEX，以解释代理行为并建立用户信任。实验结果表明，CODEX方法能够保留时间和实体信息，构建代理行为的总结。此外，对游戏环境中的离散+连续游戏状态潜在表示进行聚类，可以确定最关键的情节事件，展示了潜在空间和语义空间之间的关系。这项研究以自然语言处理技术为基础，为解锁RL在广泛应用中的潜力做出了贡献。

CODEX：一种基于聚类的可解释强化学习方法