Researcher · Academic
Caglar Gulcehre
École Polytechnique Fédérale de LausanneAssistant ProfessorStealth StartupCSO
Gulcehre helped develop benchmarks and methods for offline reinforcement learning, where an AI learns from previously collected experience instead of experimenting live.[1] After six years at DeepMind, he founded EPFL's CLAIRE lab to study safer, more efficient agents and foundation models.
Career & education
École Polytechnique Fédérale de Lausanne2023-present
Microsoft AI2025-2026
Google DeepMind2017-2023
Bahcesehir University
Middle East Technical University
Université de MontréalWork and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Citation Trend
Selected contributions
Grandmaster level in StarCraft II using multi-agent reinforcement learning
With Oriol Vinyals, Igor Babuschkin, Wojciech Czarnecki, Michaël Mathieu, Andrew Dudzik, Junyoung Chung, David H. Choi and others ·AlphaStar reached Grandmaster level in StarCraft II through competitive AI training.
References
- RL Unpluggedarxiv.org
The team introduces datasets and tasks for comparing agents that learn from recorded experience.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
Reviewed August 8, 2026 · Checked for accuracy and new information.