Across a wide range of hardware scenarios, the computational efficiency and physical size of the arithmetic units significantly influence the speed and footprint of the overall hardware system.

Due to their inherent complexity, these tasks pose significant challenges for current machine learning systems.

As such, we prevent policies from merely exploiting heuristic rewards without improving the task reward.

Our experimental results demonstrate that the ranking algorithm-based classifiers provide plans that enhance infection rate control, especially with increased action budgets for small networks.

Training a policy in a source domain for deployment in the target domain under a dynamics shift can be challenging, often resulting in performance degradation.