Irregular data access patterns in high-performance computing and intelligent computing often render traditional data prefetching techniques ineffective. Existing models that rely on fixed rules or offline learning based on specific program contexts also struggle to adapt to dynamically changing memory access patterns during runtime. While the Pythia reinforcement learning (RL) prefetching framework demonstrates adaptability through online learning, it still requires manual tuning under extreme irregular workloads, limiting its generalization in practical applications. This paper proposes IEP (Irregular Enhanced Pythia), a context-aware reinforcement learning prefetching framework to enhance the prediction capability for irregular memory access patterns. The framework introduces two key innovations. The first is an irregular feature enhancement module. It incorporates address bit masks and access sequence distance as state features to capture hidden spatiotemporal patterns in memory allocator behavior, thereby improving the representation of irregular memory accesses. The second is a hierarchical reward strategy module, which employs a dynamic reward mechanism combining confidence awareness and bandwidth sensitivity. This mechanism finely guides the agent’s learning process, accelerating policy optimization and improving final performance. Experiments were conducted using the ChampSim simulator, to test various irregular workloads. Results show that compared to the Pythia framework, the proposed solution achieves a maximum improvement of 2.27% in average prefetching accuracy and 2.90% in average single-core IPC for typical irregular workloads such as Ligra and PARSEC, while maintaining stable performance in multi-core environments.