Ilya Kostrikov is a research scientist at OpenAI. His personal site and papers document sample-efficient deep RL, including Implicit Q-Learning (IQL) for offline RL. OpenAI's o1 contributions materials list him among major contributors to the reasoning model effort.123
At a glance
- Current role
- Research scientist
- Company
- OpenAI
- Sources cited
- 3
- Profile reviewed
Accomplishments
Offline RL and OpenAI
Kostrikov coauthored Implicit Q-Learning, an offline RL method that improves policies from static datasets without evaluating out-of-distribution actions. At OpenAI his work has included RLHF/post-training themes and contributions credited on o1.213
Timeline
- IQL offline RL paper.2
Where they work
- OpenAI 102 people in the wiki
Related people
- Aravind SrinivasAlso at OpenAI
- Karl CobbeAlso at OpenAI
- John SchulmanAlso at OpenAI
- Jakub PachockiAlso at OpenAI
- Jonathan GordonAlso at OpenAI
- Younes BelkadaLanguage models · Reinforcement learning
- Mika SenghaasReinforcement learning · Language models
- Sami JaghouarReinforcement learning · Language models
- Lilian WengLanguage models · Reinforcement learning
- Giambattista ParascandoloLanguage models · Reinforcement learning
Suggest a correction or removal
Profiles cover public professional work only, and each statement cites a source. If something is out of date, missing or wrong, tell us and link a source. People can also ask for their profile to be corrected or removed.
References
3 sources · profile reviewed Oct 24, 2026 · data updated Oct 24, 2026