Autonomous underwater vehicles are required to perform multiple tasks adaptively and in an explainable manner under dynamic, uncertain conditions and limited sensing, challenges that classical controllers struggle to address. This demands robust, generalizable, and inherently interpretable control policies for reliable long-term monitoring. Reinforcement learning, particularly multi-task RL, overcomes these limitations by leveraging shared representations to enable efficient adaptation across tasks and environments. However, while such policies show promising results in simulation and controlled experiments, they yet remain opaque and offer limited insight into the agent's internal decision-making, creating gaps in transparency, trust, and safety that hinder real-world deployment. The internal policy structure and task-specific specialization remain poorly understood. To address these gaps, we analyze the internal structure of a pretrained multi-task reinforcement learning network in the HoloOcean simulator for underwater navigation by identifying and comparing task-specific subnetworks responsible for navigating toward different species. We find that in a contextual multi-task reinforcement learning setting with related tasks, the network uses only about 1.5% of its weights to differentiate between tasks. Of these, approximately 85% connect the context-variable nodes in the input layer to the next hidden layer, highlighting the importance of context variables in such settings. Our approach provides insights into shared and specialized network components, useful for efficient model editing, transfer learning, and continual learning for underwater monitoring through a contextual multi-task reinforcement learning method.

翻译：自主水下航行器需在动态、不确定环境及有限感知条件下，以可解释的方式自适应完成多项任务，这是经典控制器难以应对的挑战。这要求具备稳健、可泛化且固有可解释的控制策略，以实现可靠的长期监测。强化学习（尤其是多任务强化学习）通过利用共享表征实现跨任务与环境的有效自适应，克服了上述局限。然而，尽管此类策略在仿真与受控实验中展现出前景，其决策过程仍不透明，对智能体内部决策机制的洞察有限，导致在透明度、可信度与安全性方面存在缺口，阻碍了实际部署。当前对策略内部结构及任务特定专业化机制的理解仍显不足。为弥补这些不足，我们通过识别并比较负责导航至不同物种的任务特定子网络，分析了用于水下导航的预训练多任务强化学习网络在HoloOcean模拟器中的内部结构。研究发现，在涉及相关任务的上下文多任务强化学习场景中，网络仅使用约1.5%的权重区分不同任务。其中，约85%的此类权重连接输入层中的上下文变量节点与下一隐藏层，凸显了上下文变量在此类设置中的关键作用。该方法揭示了共享与专用网络组件的特性，有助于通过上下文多任务强化学习方法实现水下监测中的高效模型编辑、迁移学习与持续学习。