- Software engineer, RL, Google DeepMind31
Manuel Kroiss is a software engineer on DeepMind's reinforcement learning team and an equal-contribution co-author of the Nature paper "Grandmaster level in StarCraft II using multi-agent reinforcement learning," documenting AlphaStar. He has also publicly discussed Python GIL bottlenecks in large-scale DeepMind RL systems in the context of PEP 703.123
At a glance
- Current role
- Software engineer, RL
- Company
- Google DeepMind
- Fields
- Reinforcement learning, Agents
- Sources cited
- 3
- Profile reviewed
Accomplishments
AlphaStar
Kroiss is listed among equal contributors who designed and built AlphaStar, DeepMind's multi-agent RL system that reached Grandmaster level in StarCraft II under full-game conditions.12
Timeline
- AlphaStar Grandmaster Nature paper published.1
Where they work
- Google DeepMind 84 people in the wiki
Related people
- Shimon WhitesonAlso at Google DeepMind
- Jeff CluneAlso at Google DeepMind
- Timothy LillicrapAlso at Google DeepMind
- Richard SuttonAlso at Google DeepMind
- Adam GleaveAlso at Google DeepMind
- Kenneth StanleyReinforcement learning · Agents
- Josh AlbrechtAgents · Reinforcement learning
- Katja HofmannReinforcement learning · Agents
- Jakob FoersterReinforcement learning · Agents
- Noam BrownReinforcement 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 If something is out of date, missing or wrong, tell us and link a source.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
3 sources · profile reviewed Oct 24, 2026 · data updated Oct 24, 2026