PeopleofSuperintelligence

Researcher

Alekh Agarwal

Alekh Agarwal is a machine learning researcher whose work spans reinforcement learning theory, bandits and learning from human preferences. He earned a computer science and engineering B.Tech. at IIT Bombay in 2007 and a PhD in Electrical Engineering and Computer Sciences at UC Berkeley in 2012, then led Microsoft Research’s Reinforcement Learning Research group before moving to Google Research in 2021. His work includes “Fast Convergence of Regularized Learning in Games,” which won a NeurIPS Best Paper Award in 2015, and ATAC, an offline reinforcement learning algorithm that earned ICML 2022 Outstanding Paper Runner-Up. In 2019, he was part of Microsoft’s team whose Decision Service won the inaugural ACM SIGAI Industry Award, and he served as a co-program chair for NeurIPS in 2022. He coauthored a 2025 theoretical study of offline preference-based reinforcement learning and served as an ICML Program Chair in 2026; as of October 2026, he is a researcher in Google’s Learning Theory team.

Badges

Timeline

  1. 2007–2012

    IIT Bombay and Berkeley degrees

    He earns a B.Tech. in computer science and engineering at IIT Bombay in 2007 and completes a PhD in Electrical Engineering and Computer Sciences at UC Berkeley in 2012.

  2. 2012–2021

    Leading Microsoft’s reinforcement learning group

    From 2012 to 2021, he works at Microsoft Research and leads its Reinforcement Learning Research group, then moves to Google Research in 2021.

  3. 2015

    A NeurIPS best paper

    With Vasilis Syrgkanis, Haipeng Luo and Robert Schapire, he coauthors “Fast Convergence of Regularized Learning in Games,” which wins a Best Paper Award at NeurIPS in 2015. The paper shows how regularized learning algorithms reach approximate efficiency and coarse correlated equilibria faster in multiplayer normal-form games.

  4. 2019

    A Microsoft decision service

    Microsoft’s Real World Reinforcement Learning team includes him when it wins the inaugural ACM SIGAI Industry Award in 2019 for its Decision Service.

  5. 2022

    ATAC earns an ICML award

    In 2022, he coauthors ATAC, a model-free offline reinforcement learning algorithm based on relative pessimism, and the paper earns the ICML Outstanding Paper Runner-Up award.

  6. 2022

    Co-chairing NeurIPS

    He serves as a co-program chair for NeurIPS in 2022.

  7. 2025

    Offline preference learning

    In 2025, he coauthors “Design Considerations in Offline Preference-based RL,” a theoretical study of design choices in offline reinforcement learning from human preferences.

  8. As of October 2026

    Google researcher and ICML chair

    In 2026, he serves as an ICML Program Chair. As of October 2026, he is a researcher in Google’s Learning Theory team, where his work includes reinforcement learning, bandits, active learning and online learning.

Career

  1. Since 2021Google ResearchResearcher, Learning Theory team
  2. 2012–2021Microsoft ResearchLead, Reinforcement Learning Research group

Education

  1. 2012University of California, BerkeleyPhD in Electrical Engineering and Computer Sciences
  2. 2007IIT BombayB.Tech. in computer science and engineering

From the biography.

Videos

YouTube videos in which Alekh Agarwal speaks or appears, newest first. A model chose them from YouTube search results. List updated 21 October 2026.

  1. Interactive Machine Learning Systems with Alekh Agarwal - #17The TWIML AI Podcast with Sam Charrington · 6 April 2017 · 35 min

Video data from YouTube API Services. By watching you agree to the YouTube Terms of Service. How we use YouTube data.

  1. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes Alekh Agarwal. We estimate that alumni of 17 major AI labs went on to found or lead 350 other organizations, including 226 they founded, and we trace 472 career moves directly between 23 labs since 2010.
  2. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Alekh Agarwal. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  3. Google had the most people shaping AI every year from 2014 to 2025Includes Google. Our estimates of which organizations employed the most people shaping AI each year from 1955 to 2025, tracing the shift from university labs to companies.
  4. Google has the highest combined h-index among AI organizationsIncludes Google. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI organizations.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Alekh Agarwal yet. Send us a free-licensed photo.

  1. Young Alumnus Achiever - Indian Institute of Technology Bombay acr.iitbombay.org. Checked 21 October 2026.
  2. Computational Trade-offs in Statistical Learning | EECS at UC Berkeley www2.eecs.berkeley.edu. Checked 21 October 2026.
  3. Dr. Alekh Agarwal - Indian Institute of Technology Bombay acr.iitbombay.org. Checked 21 October 2026.
  4. NIPS 2015 Awards neurips.cc. Checked 21 October 2026.
  5. Fast Convergence of Regularized Learning in Games papers.neurips.cc. Checked 21 October 2026.
  6. ACM SIGAI Industry Award - ACM SIGAI sigai.acm.org. Checked 21 October 2026.
  7. Foundations of Real-World Reinforcement Learning - Microsoft Research microsoft.com. Checked 21 October 2026.
  8. Adversarially Trained Actor Critic for Offline Reinforcement Learning proceedings.mlr.press. Checked 21 October 2026.
  9. ICML 2022 Awards | ICML 2022 icml.cc. Checked 21 October 2026.
  10. 2022 Organizing Committee neurips.cc. Checked 21 October 2026.
  11. Design Considerations in Offline Preference-based RL proceedings.mlr.press. Checked 21 October 2026.
  12. ICML 2026 Committees icml.cc. Checked 21 October 2026.
  13. Alekh Agarwal research.google. Checked 21 October 2026.