🧑‍🔬 Igor Babuschkin

🏛️ Affiliations

🎓University of ManchesterManchester · United Kingdom2016–2019 · 91 papers🔬Centro Brasileiro de Pesquisas FísicasRio de Janeiro · Brazil2016–2017 · 16 papers🎓University of ZurichZurich · Switzerland2016–2017 · 11 papers🔬Istituto Nazionale di Fisica Nucleare, Sezione di FerraraFerrara · Italy2017–2018 · 5 papers🏢Google DeepMindLondon · United Kingdom2019–2022 · 3 papers🔬European Organization for Nuclear ResearchGeneva · Switzerland2016–2019 · 3 papers🏢GoogleMountain View · United States2015–2018 · 3 papers🎓Heidelberg UniversityHeidelberg · Germany2016–2018 · 3 papers🎓University of GroningenGroningen · Netherlands2017–2018 · 2 papers🔬Centre National de la Recherche ScientifiqueParis · France2016–2017 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 10 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. Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets (2022 · 177 citations)
   Why heavily overparameterized networks generalize instead of simply memorizing their training data is still poorly understood.
2. Formal Mathematics Statement Curriculum Learning (2022 · 133 citations)
   Neural theorem provers for formal mathematics lack the self-play mechanism that drives progress in two-player games.

All works

11 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. Grandmaster level in StarCraft II using multi-agent reinforcement learning ↗Nature · no summary yetOriol Vinyals et al.2019 · 3,577 citations
2. Scaling Language Models: Methods, Analysis & Insights from Training Gopher ↗arXiv:2112.11446 · no summary yetJack W. Rae et al.2021 · 928 citations
3. Parallel WaveNet: Fast High-Fidelity Speech Synthesis ↗arXiv (Cornell University) · no summary yetAäron van den Oord et al.2017 · 403 citations
4. Grokking: Generalization Beyond Overfitting on Small Algorithmic DatasetsarXiv:2201.02177Alethea Power, Yuri Burda, Harri Edwards, et al.2022 · 177 citations
5. Relational Deep Reinforcement Learning ↗arXiv (Cornell University) · no summary yetVinícius Zambaldi et al.2018 · 160 citations
6. Synthesizing Programs for Images using Reinforced Adversarial Learning ↗arXiv (Cornell University) · no summary yetYaroslav Ganin et al.2018 · 136 citations
7. Formal Mathematics Statement Curriculum LearningarXiv:2202.01344Stanislas Polu, Jesse Michael Han, Kunhao Zheng, et al.2022 · 133 citations
8. Deep reinforcement learning with relational inductive biases ↗International Conference on Learning Representations · no summary yetVinícius Zambaldi et al.2018 · 132 citations
9. Unsupervised Doodling and Painting with Improved SPIRAL ↗arXiv (Cornell University) · no summary yetJohn F. J. Mellor et al.2019 · 24 citations
10. Unsupervised Neural Machine Translation with Generative Language Models Only ↗arXiv (Cornell University) · no summary yetJesse Michael Han et al.2021 · 22 citations
11. AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning ↗arXiv (Cornell University) · no summary yetMichaël Mathieu et al.2023 · 7 citations

🤝 Co-authors here

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

• Harri Edwards
• Ilya Sutskever
• Jesse Michael Han
• Kunhao Zheng
• Mantas Baksys
• Stanislas Polu
• Vedant Misra
• Yuri Burda

Venues

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

• Science
• International Conference on Learning Representations
• Nature

🔗 Cited by

Papers of our library cite their works 12,380 times (of the 149,439 papers whose bibliographies we read); 2,628 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

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