- Professor of Computer Science, University of Oxford1
- Research Director, Google DeepMind1
Shimon Whiteson is a Professor of Computer Science at the University of Oxford and a Research Director at Google DeepMind, with research on deep reinforcement learning and imitation learning applied to robotics and video games. Before Oxford, Whiteson was an Assistant and then Associate Professor at the University of Amsterdam, and Whiteson's spin-out company Latent Logic was acquired by Waymo in 2019. Whiteson is the last-listed author of the multi-agent reinforcement learning papers QMIX (2018) and Counterfactual Multi-Agent Policy Gradients (COMA, 2017).123
At a glance
- Current roles
- Professor of Computer Science +1 more
- Companies
- University of Oxford, Google DeepMind
- Sector
- University
- Fields
- Reinforcement learning, Agents
- Education
- UT Austin, Oxford
- Work listed
- 2
- Honors
- 3
- Sources cited
- 5
- Profile reviewed
Career
Shimon Whiteson completed a doctorate at the University of Texas at Austin in 2007 and spent eight years as an assistant and then associate professor at the University of Amsterdam. Whiteson joined the University of Oxford as an associate professor in 2015 and is now a Professor of Computer Science there, where Whiteson heads the Whiteson Research Lab.1
Whiteson's spin-out company, Latent Logic, was acquired by Waymo in 2019. Whiteson is also a Research Director at Google DeepMind.1
Research
Whiteson's research centres on deep reinforcement learning and imitation learning, with applications in robotics and video games. Several of Whiteson's papers address cooperative multi-agent learning: Whiteson is last-listed author of a 2016 paper in which agents learn communication protocols with deep reinforcement learning, of the COMA counterfactual policy gradient method (2017), and of the QMIX value-factorisation method (2018).1432
Whiteson is also last-listed author of the StarCraft Multi-Agent Challenge (2019), a benchmark for cooperative multi-agent reinforcement learning built on StarCraft II micromanagement scenarios.5
Work and contributions
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning Published research
Senior (last) author of the 2018 paper on learning joint action-values for teams of agents trained centrally and executed in a decentralised way.2
Counterfactual Multi-Agent Policy Gradients (COMA) Published research
Senior (last) author of the 2017 paper proposing the COMA multi-agent actor-critic method with a centralised critic.3
Timeline
- Completed a doctorate at the University of Texas at Austin.1
- Joined the University of Oxford as an associate professor after eight years at the University of Amsterdam.1
- Co-authored "Learning to Communicate with Deep Multi-Agent Reinforcement Learning".4
- Co-authored "Counterfactual Multi-Agent Policy Gradients" (COMA) as last-listed author.3
- Co-authored the QMIX paper on monotonic value function factorisation as last-listed author.2
- Latent Logic, Whiteson's spin-out company, was acquired by Waymo.1
- Co-authored "The StarCraft Multi-Agent Challenge" benchmark paper.5
Other documented roles
Roles the sources document that are not confirmed as current.
Honors and recognition
Where they work
- University of Oxford 3 people in the wiki
- Google DeepMind 64 people in the wiki
Related people
- Jakob FoersterAlso at University of Oxford
- Andrea VedaldiAlso at University of Oxford
- David HaReinforcement learning · Agents
- Siddharth NarayananReinforcement learning · Agents
- Noam BrownReinforcement learning · Agents
- Jeff CluneReinforcement learning · Agents
- Denis YaratsReinforcement learning · Agents
- Kenneth StanleyReinforcement learning · Agents
- Josh AlbrechtAgents · Reinforcement learning
- Katja HofmannReinforcement learning · Agents
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
5 sources · profile reviewed Oct 21, 2026 · data updated Oct 21, 2026
- Shimon Whiteson — Whiteson Research Lab, University of Oxford
- QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning (arXiv 1803.11485)
- Counterfactual Multi-Agent Policy Gradients (arXiv 1705.08926)
- Learning to Communicate with Deep Multi-Agent Reinforcement Learning (arXiv 1605.06676)
- The StarCraft Multi-Agent Challenge (arXiv 1902.04043)