Faster sorting algorithms discovered using deep reinforcement learning

ABSTRACT

Fundamental algorithms such as sorting or hashing are used trillions of times on any given day. As demand for computation grows, it has become critical for these algorithms to be as performant as possible. We demonstrate that artificial intelligence can discover faster algorithms for fundamental computation tasks. We introduce AlphaDev, an artificial intelligence system that uses reinforcement learning to discover enhanced computer science algorithms—surpassing those honed by scientists and engineers over decades. AlphaDev discovered faster sorting and hashing algorithms by playing an assembly game, leading to improvements in the LLVM libc++ standard sorting library that are now used by millions of developers globally.