AI People Wiki

Builders & open source

Timothy Lillicrap

Director of Research, Google DeepMind

  • Director of Research, Google DeepMind1
  • Program Co-Director, Learning in Machines & Brains, CIFAR1

Timothy Lillicrap is a Director of Research at Google DeepMind, which Lillicrap joined as a research scientist in 2014, and a Program Co-Director of CIFAR's Learning in Machines & Brains program. Lillicrap's research focuses on machine learning for optimal control and decision-making and on using these frameworks to understand how the brain learns. Lillicrap is first author of "Continuous control with deep reinforcement learning" (2015), which presents an actor-critic algorithm based on the deterministic policy gradient for continuous action spaces, and a co-author of the AlphaZero and A3C papers.1234

At a glance

Current roles
Director of Research +1 more
Sector
Company
Education
Oxford
Work listed
2
Sources cited
7
Profile reviewed

Career

Timothy Lillicrap earned a PhD in systems neuroscience at Queen's University. Lillicrap then worked as a postdoctoral research fellow at the University of Oxford from 2012.1

Lillicrap joined Google DeepMind as a research scientist in 2014 and is now a Director of Research there. Lillicrap is also a Program Co-Director of CIFAR's Learning in Machines & Brains program.1

Research

Lillicrap's research applies machine learning to optimal control and decision-making and uses the same mathematical frameworks to study how the brain learns. A 2014 paper with Lillicrap as first author showed that random feedback weights can support learning in deep networks, offering an alternative to exact backpropagation.15

In deep reinforcement learning, Lillicrap was first author of the DDPG paper on continuous control (2015) and a co-author of A3C (2016), AlphaZero (2017) and MuZero (2019), which plans with a learned model to play Atari, Go, chess and shogi. Lillicrap also co-authored Dreamer (2019), which learns behaviours by imagining trajectories in a learned latent model.24367

Work and contributions

  • Continuous control with deep reinforcement learning Published research

    First author of the 2015 paper presenting an actor-critic, model-free algorithm based on the deterministic policy gradient that operates over continuous action spaces.2

  • AlphaZero and A3C Published research

    Co-author of "Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm" (2017) and of "Asynchronous Methods for Deep Reinforcement Learning" (2016).34

Timeline

  1. Became a postdoctoral research fellow at the University of Oxford.1
  2. Joined Google DeepMind as a research scientist.1
  3. Published "Random feedback weights support learning in deep neural networks" as first author.5
  4. Published "Continuous control with deep reinforcement learning", introducing DDPG, as first author.2
  5. Co-authored "Asynchronous Methods for Deep Reinforcement Learning", introducing A3C.4
  6. Co-authored the AlphaZero paper on mastering chess and shogi by self-play.3
  7. Co-authored the MuZero paper on planning with a learned model.6
  8. Co-authored "Dream to Control", the paper introducing the Dreamer agent.7

Where they work

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

7 sources · profile reviewed Oct 21, 2026 · data updated Oct 21, 2026

  1. Timothy Lillicrap — CIFAR bioCIFAR · Official page · accessed Oct 21, 2026
  2. Continuous control with deep reinforcement learning (arXiv 1509.02971)arXiv · Paper · published Sep 9, 2015 · accessed Oct 21, 2026
  3. Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm (arXiv 1712.01815)arXiv · Paper · published Dec 5, 2017 · accessed Oct 21, 2026
  4. Asynchronous Methods for Deep Reinforcement Learning (arXiv 1602.01783)arXiv · Paper · published Feb 4, 2016 · accessed Oct 21, 2026
  5. Random feedback weights support learning in deep neural networks (arXiv 1411.0247)arXiv · Paper · published Nov 2, 2014 · accessed Oct 21, 2026
  6. Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model (arXiv 1911.08265)arXiv · Paper · published Nov 19, 2019 · accessed Oct 21, 2026
  7. Dream to Control: Learning Behaviors by Latent Imagination (arXiv 1912.01603)arXiv · Paper · published Dec 3, 2019 · accessed Oct 21, 2026