A Reinforcement Learning Environment for Polyhedral Optimizations

no code implementations • 28 Apr 2021 • Alexander Brauckmann, Andrés Goens, Jeronimo Castrillon

Existing problem formulations in state-of-the-art heuristics depend on the shape of particular loops, making it hard to leverage generic and more powerful optimization techniques from the machine learning domain.

BIG-bench Machine Learning reinforcement-learning +1