Learning-Aided Heuristics Design for Storage System
This work addresses the need for transparent and efficient algorithms in storage systems, offering a practical improvement over existing methods, though it appears incremental in combining learning with heuristic design.
The paper tackles the problem of designing interpretable, white-box algorithms for storage systems by proposing a learning-aided heuristic method that automatically generates human-readable strategies from Deep Reinforcement Learning agents. The result shows that this solution outperforms default settings and handcrafted strategies by human experts in a storage resource allocation scenario.
Computer systems such as storage systems normally require transparent white-box algorithms that are interpretable for human experts. In this work, we propose a learning-aided heuristic design method, which automatically generates human-readable strategies from Deep Reinforcement Learning (DRL) agents. This method benefits from the power of deep learning but avoids the shortcoming of its black-box property. Besides the white-box advantage, experiments in our storage productions resource allocation scenario also show that this solution outperforms the systems default settings and the elaborately handcrafted strategy by human experts.