Autonomous agents operating in real-world scenarios frequently encounter uncertainty and make decisions based on incomplete information.

Despite the success of neural-based combinatorial optimization methods for end-to-end heuristic learning, out-of-distribution generalization remains a challenge.

Precise hardware performance models play a crucial role in code optimizations. They can assist compilers in making heuristic decisions or aid autotuners in identifying the optimal configuration for a given program.

This paper focuses on the methods that explain what neurons learn during the training process.

We demonstrate that this assumption imposes performance limitations in particular on difficult problem instances.

Then momentum acceleration is also introduced into our dual accelerating update step.