🧑‍🔬 Peter L. Bartlett

🏛️ Affiliations

🎓University of California, BerkeleyBerkeley · United States2002–2026 · 175 papersEmployment since 2003current🏢GoogleMountain View · United States2021–2026 · 7 paperscurrent🏢Google DeepMindLondon · United Kingdom2023–2026 · 4 paperscurrent🤝Simons FoundationNew York · United States2023–2026 · 3 paperscurrent🏢Adobe SystemsSan Jose · United States2026 · 1 papercurrent🎓Australian National UniversityCanberra · Australia1993–2025 · 104 papers🎓Queensland University of TechnologyBrisbane · Australia2012–2019 · 13 papers🎓The University of QueenslandBrisbane · Australia1991–1993 · 7 papersEducation🔬Lawrence Berkeley National LaboratoryBerkeley · United States2018 · 3 papers🎓The University of MelbourneMelbourne · Australia2007 · 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

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. RL²: Fast Reinforcement Learning via Slow Reinforcement Learning (2016 · 524 citations)
   Deep RL agents usually need enormous amounts of experience: mastering one Atari game can take the equivalent of about 40 days of nonstop play, while a human needs roughly two hours.
2. Fast Best-of-N Decoding via Speculative Rejection (2024 · 50 citations)
   Best-of-N aligns an LLM at inference time without retraining. It samples many candidate answers and keeps the one a reward model rates highest. It can rival post-training methods such as RLHF or DPO, but competitive N values run into the thousands, which would need many accelerators. The authors observe that reward…

All works

4 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. RL²: Fast Reinforcement Learning via Slow Reinforcement LearningarXiv:1611.02779Yan Duan, John Schulman, Xi Chen, et al.2016 · 524 citations
2. Fast Best-of-N Decoding via Speculative RejectionConference on Neural Information Processing Systems (NeurIPS)Hanshi Sun, Momin Haider, Ruiqi Zhang, et al.2024 · 50 citations
3. A Learning-Based Approach to Reactive Security ↗IEEE Transactions on Dependable and Secure Computing · no summary yetAdam Barth et al.2011 · 43 citations
4. Agnostic learning with unknown utilities ↗arXiv (Cornell University) · no summary yetKush Bhatia et al.2021 · 2 citations

🤝 Co-authors here

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

• Andrea Zanette
• Ilya Sutskever
• Jiahao Qiu
• John Schulman
• Mengdi Wang
• Ming Yin
• Pieter Abbeel
• Ruiqi Zhang
• Xi Chen

Venues

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

• Conference on Neural Information Processing Systems (NeurIPS): NeurIPS 2024
• IEEE Transactions on Dependable and Secure Computing

🔗 Cited by

Papers of our library cite their works 116 times (of the 149,439 papers whose bibliographies we read); 32 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/peter-l-bartlett/