Adam Gleave
Co-founder and CEO of FAR.AI; researcher on adversarial robustness and reward learning
- Co-founder and CEO (since January 2022), FAR.AI124
- Board director (since May 2024), METR (Model Evaluation & Threat Research)43
- Trustee and director (since July 2024), London Initiative for Safe AI (LISA)4
- Director (since December 2024), Safe AI Forum (SAIF)4
Adam Gleave is the co-founder and CEO of FAR.AI, an AI safety research nonprofit, where Gleave sets the overall research agenda and manages the technical staff. Gleave completed a PhD in artificial intelligence at UC Berkeley advised by Stuart Russell, and has published on adversarial policies, reward learning and the robustness of language models.134
Career
Gleave completed a PhD in artificial intelligence at UC Berkeley from 2017 to 2022, advised by Stuart Russell, with a thesis titled "Towards Trustworthy Machine Learning". During the PhD, Gleave was a research intern at DeepMind in 2019 and 2021, working with Geoffrey Irving and Jan Leike.43
Gleave co-founded FAR.AI in January 2022 and serves as its CEO. Gleave also serves on the boards of METR (since May 2024), the London Initiative for Safe AI (since July 2024) and the Safe AI Forum (since December 2024).413
Research
Gleave's research concerns making advanced AI systems verifiably safe, ranging from value learning and robustness in deep reinforcement learning to detecting hidden or deceptive behavior in frontier models. The 2019 paper "Adversarial Policies: Attacking Deep Reinforcement Learning" and the 2022 paper "Adversarial Policies Beat Superhuman Go AIs" studied how trained agents can be exploited by adversarial opponents.156
Gleave's reward-learning work includes "Quantifying Differences in Reward Functions" (ICLR 2021) and the imitation library of clean imitation learning implementations. Later work with FAR.AI colleagues covers scaling trends in language model robustness (ICML 2025) and deception probes in reinforcement learning from verifiable rewards (ICML 2026).47
Work
Adversarial Policies: Attacking Deep Reinforcement Learning (external site: arxiv.org)Published research
First author of the 2019 paper, presented at ICLR 2020, which showed that reinforcement learning agents can be defeated by adversarial opponent policies.54
Adversarial Policies Beat Superhuman Go AIs (external site: arxiv.org)Published research
Co-author of the 2022 paper on adversarial attacks against Go-playing AI systems, an ICML 2023 oral paper that received a best paper award at the NeurIPS ML Safety Workshop 2022.64
imitation: Clean Imitation Learning Implementations (external site: arxiv.org)Open-source code
First author of the 2022 report describing the imitation library of imitation and reward learning algorithm implementations.73
Career timeline
2017
Began a PhD in artificial intelligence at UC Berkeley, advised by Stuart Russell.4
May 2019
Posted "Adversarial Policies, Attacking Deep Reinforcement Learning" as first author.5
2022
Completed the PhD at UC Berkeley with a thesis titled "Towards Trustworthy Machine Learning".4
Jan 2022
Co-founded FAR.AI and became its CEO.4
Nov 2022
Co-authored "Adversarial Policies Beat Superhuman Go AIs" and released the imitation library report.67
May 2024
Joined the board of METR as a director.4
Dec 2024
Became a director of the Safe AI Forum.4
Other documented roles
Roles the sources document but that are not confirmed as current.
Honors and recognition
- Best Paper Award, NeurIPS ML Safety Workshop (for "Adversarial Policies Beat Superhuman Go AIs") · NeurIPS ML Safety Workshop, 20224
Related people
More sourced profiles at the same organization, in the same field, or from the same school.
- Ajeya CotraAlso at METR
- Jan LeikeAlso at DeepMind
- Alex SmolaAlso from UC Berkeley
- Beth BarnesAlso at METR
- Paul ChristianoAlso from UC Berkeley
- Alexei A. EfrosAlso from UC Berkeley
- Hjalmar WijkAlso at METR
- Shengjia ZhaoReinforcement learning
- Ali GhodsiAlso from UC Berkeley
- Karl BerzinsAlso at FAR.AI
- Wojciech ZarembaSafety and alignment
- Anca DraganAlso at Google DeepMind
Is this you?
Profiles cover public professional work only, and every line cites a source. If something is out of date, missing or wrong, send a correction with a link to an official page and we will update it. Suggest a correction
Add this badge to your website or GitHub profile README. It links back to this page. It is not an endorsement or a rating.
Markdown (for a README)
[](https://unitedstatesofamericasuperintelligence.com/people/adam-gleave/)
HTML
<a href="https://unitedstatesofamericasuperintelligence.com/people/adam-gleave/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/profile.svg" alt="Adam Gleave — Profile on USASI" height="20"></a>
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.