ICARL Seminar Series - 2023 Spring
AlphaDev: Faster sorting algorithms discovered using deep reinforcement learning sequences.
Seminar by Daniel Mankowitz and Andrea Michi (Google DeepMind).
Abstract:
Fundamental algorithms such as sorting or hashing are used trillions of times on any given day1. 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 past2, 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 library3. 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.
About the speakers:
Daniel Mankowitz is a Staff Research Scientist at Google Deepmind, working on solving the key challenges in Reinforcement Learning algorithms that unlock real-world applications at scale. This includes a focus on Reinforcement Learning from Human Feedback (RLHF) in the context of Large Language Models (LLMs). Mankowitz has worked on: code optimization, code generation, video compression, recommender systems, and controlling physical systems such as Heating Ventilation and Air-Conditioning (HVAC), with publications in Nature and Science.
Andrea Michi is a Senior Research Engineer at Google DeepMind working on Reinforcement Learning applications. Michi has worked on a range of domains including renewable forecasting, code optimization, control of physical systems such as Heating Ventilation and Air-Conditioning (HVAC) and the magnetic confinement in a Tokamak. More recently, Michi has focused on Reinforcement Learning from Human Feedback (RLHF) to align Large Language Models (LLMs) to human preferences.
------------------
Links
Daniel Mankowitz
Site: danielmankowitz.wixsite.com/danielm
Twitter: dj_mankowitz
Andrea Michi
Site: andreamichi.com/
Twitter: andreamichi
ICARL
Site: icarl.doc.ic.ac.uk
Twitter: ic_arl
RU-vid: @ICARLSeminars
------------------
4 окт 2024
