Tobias Pohlen
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Grandmaster level in StarCraft II using multi-agent reinforcement learningSaved credit: Contributor · 2019Explore people connected to this work →
- Scaling Language Models: Methods, Analysis & Insights from Training GopherSaved credit: Contributor · 2021Explore people connected to this work →
- A data-driven approach for learning to control computersSaved credit: Contributor · 2022Explore people connected to this work →
- Full-Resolution Residual Networks for Semantic Segmentation in Street ScenesSaved credit: Contributor · 2016Explore people connected to this work →
- Reward learning from human preferences and demonstrations in AtariSaved credit: Contributor · 2018Explore people connected to this work →