Reinforcement Learning (RL) environments can produce training data with spurious correlations between features due to the amount of training data or its limited feature coverage. This can lead to RL agents encoding these misleading correlations in their latent representation, preventing the agent from generalising if the correlation changes within the environment or when deployed in the real world. Disentangled representations can improve robustness, but existing disentanglement techniques that minimise mutual information between features require independent features, thus they cannot disentangle correlated features. We propose an auxiliary task for RL algorithms that learns a disentangled representation of high-dimensional observations with correlated features by minimising the conditional mutual information between features in the representation. We demonstrate experimentally, using continuous control tasks, that our approach improves generalisation under correlation shifts, as well as improving the training performance of RL algorithms in the presence of correlated features.

翻译：强化学习环境可能因训练数据量或特征覆盖有限而产生特征间的虚假相关性，导致智能体在潜在表征中编码此类误导性关联。若环境内部或实际部署中相关性发生变化，将阻碍智能体实现泛化。解耦表示可提升鲁棒性，但现有最小化特征间互信息的解耦技术需假设特征独立，因此无法解耦相关特征。我们提出一种面向强化学习算法的辅助任务，通过最小化表征中特征间的条件互信息，学习高维观测数据中相关特征的解耦表示。在连续控制任务上的实验表明，该方法不仅能提升相关性偏移下的泛化能力，还能在存在相关特征时改善强化学习算法的训练性能。