Andrea Michi
Andrea Michi has 2 papers in our library, in 2023; often with Daniele Calandriello, Mark Rowland, Matthieu Geist.
OpenAlex · ORCID · h-index 4 · 9 works · 278 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 77 times in our library · ⭐ Paper Stars ranking: #6377
Affiliations
🏢Google DeepMindLondon ·
United Kingdom2019–2024 · 3 papersEmployment🎓Imperial College LondonLondon ·
United Kingdom2019 · 1 paperEducation🏢GoogleLondon ·
United KingdomEmployment
Fields, topics and concepts
📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 2 worksArtificial Intelligence · 2 worksInformation Systems · 1 workArts and Humanities · 1 workLanguage and Linguistics · 1 work
Works by year
2020s
Papers
- Faster Sorting Algorithms Discovered Using Deep Reinforcement Learning (2023 · 199 citations)
Tiny sorting routines for a handful of elements run an enormous number of times, because divide-and-conquer sorts call them on short subarrays. - Nash Learning from Human Feedback (2023 · 32 citations)
Standard RLHF reduces pairwise human judgments to a scalar reward, typically through a Bradley-Terry model, and then optimizes the LLM against that score.
Co-authors here
- Daniele Calandriello
- Mark Rowland
- Matthieu Geist
- Michal Valko
- Mohammad Gheshlaghi Azar
- Remi Munos
- Sertan Girgin
Venues
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/andrea-michi/