🧑‍🔬 Rémi Munos

🏛️ Affiliations

🔬Institut national de recherche en sciences et technologies du numériqueLe Chesnay-Rocquencourt · France2007–2026 · 64 paperscurrent🔬Centre Inria de l'Université de LilleVilleneuve-d'Ascq · France2008–2026 · 60 paperscurrent🏢Google DeepMindLondon · United Kingdom2015–2026 · 52 paperscurrent🏢Microsoft Research New EnglandCambridge · United States2014–2026 · 3 paperscurrent🏢Microsoft ResearchCambridge · United Kingdom2026 · 2 paperscurrent🎓École Normale Supérieure de LyonLyon · France2026 · 2 paperscurrent🎓Courant Institute of Mathematical SciencesNew York · United States2026 · 1 papercurrent🎓University of CambridgeCambridge · United Kingdom2026 · 1 papercurrent🏢GoogleMountain View · United States2016–2023 · 32 papers🎓Université de LilleLille · France2007–2015 · 10 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 14 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. A General Theoretical Paradigm to Understand Learning from Human Preferences (2023 · 263 citations)
   This paper by researchers at Google DeepMind provides a theoretical foundation for methods that train language models from human preferences.
2. 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.
3. Outcome-based Exploration for LLM Reasoning (2025 · 15 citations)
   Reinforcement learning that rewards only a correct final answer improves LLM math reasoning, but it also narrows the range of answers a model produces.

All works

15 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

1. Bootstrap your own latent: A new approach to self-supervised Learning ↗arXiv (Cornell University) · no summary yetJean-Bastien Grill et al.2020 · 3,531 citations
2. IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures ↗arXiv:1802.01561 · no summary yetLasse Espeholt et al.2018 · 710 citations
3. Noisy Networks for Exploration ↗arXiv (Cornell University) · no summary yetMeire Fortunato et al.2017 · 570 citations
4. Unifying Count-Based Exploration and Intrinsic Motivation ↗arXiv:1606.01868 · no summary yetMarc G. Bellemare et al.2016 · 311 citations
5. A General Theoretical Paradigm to Understand Learning from Human PreferencesarXiv:2310.12036Mohammad Gheshlaghi Azar, Mark Rowland, Bilal Piot, et al.2023 · 263 citations
6. A Study on Overfitting in Deep Reinforcement Learning ↗arXiv (Cornell University) · no summary yetChiyuan Zhang et al.2018 · 242 citations
7. Sample Efficient Actor-Critic with Experience Replay ↗arXiv (Cornell University) · no summary yetZiyu Wang et al.2016 · 220 citations
8. Automated Curriculum Learning for Neural Networks ↗arXiv:1704.03003 · no summary yetAlex Graves et al.2017 · 111 citations
9. Combining policy gradient and Q-learning ↗arXiv (Cornell University) · no summary yetBrendan O’Donoghue et al.2016 · 98 citations
10. Memory-Efficient Backpropagation Through Time ↗arXiv (Cornell University) · no summary yetAudrūnas Gruslys et al.2016 · 91 citations
11. Finite time bounds for sampling based fitted value iteration ↗International Conference on Machine Learning · no summary yetCsaba Szepesvári, Rémi Munos2005 · 60 citations
12. Nash Learning from Human FeedbackarXiv:2312.00886Remi Munos, Michal Valko, Daniele Calandriello, et al.2023 · 32 citations
13. Learning to Search with MCTSnets ↗arXiv:1802.04697 · no summary yetArthur Guez et al.2018 · 30 citations
14. Outcome-based Exploration for LLM ReasoningarXiv:2509.06941Yuda Song, Julia Kempe, Remi Munos2025 · 15 citations
15. GitSwarm: Decentralized Compounding Inference ↗arXiv (Cornell University) · no summary yetVedant Shah et al.2026

🤝 Co-authors here

10 co-authors with a page, the most papers together first.

• Daniele Calandriello ×2
• Mark Rowland ×2
• Michal Valko ×2
• Mohammad Gheshlaghi Azar ×2
• Andrea Michi
• Bilal Piot
• Daniel Guo
• Julia Kempe
• Matthieu Geist
• Sertan Girgin

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• International Conference on Machine Learning

🔗 Cited by

Papers of our library cite their works 990 times (of the 149,439 papers whose bibliographies we read); 138 citing papers with a page here →.

Updated 3 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/remi-munos/