Seminar: Machine Learning Seminar

ECE Women Community

AlphaDev – Using RL to discover improved sorting algorithms

Date: March,04,2024 Start Time: 14:30 - 15:30
Location: ZOOM
Add to:
Lecturer: Daniel Mankowitz
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. Whereas remarkable progress has been achieved in the past, making further improvements on the efficiency of these routines has proved challenging for both human scientists and computational approaches. Here we show how artificial intelligence can go beyond the current state of the art by discovering hitherto unknown routines. To realize this, we formulated the task of finding a better sorting routine as a single-player game. We then trained a new deep reinforcement learning agent, AlphaDev, to play this game. AlphaDev discovered small sorting algorithms from scratch that outperformed previously known human benchmarks. These algorithms have been integrated into the LLVM standard C++ sort library. This change to this part of the sort library represents the replacement of a component with an algorithm that has been automatically discovered using reinforcement learning. We also present results in extra domains, showcasing the generality of the approach.
Daniel Mankowitz is a Staff Research Scientist at Google Deepmind, working on solving the key challenges that will unlock Reinforcement Learning algorithms to work on real-world applications at scale. This includes a focus on Reinforcement Learning from Human Feedback (RLHF) in the context of Large Language Models (LLMs).


All Seminars
Skip to content