Jakob Foerster

Jakob obtained his Ph.D. in AI at the University of Oxford. Using deep reinforcement learning (RL), he studies how accounting for agency can address multi-agent problems, ranging from the emergence of communication to non-stationarity, reciprocity, and multi-agent credit-assignment. His papers have gained prestigious awards at top machine learning conferences (ICML, AAAI) and have helped to push deep multi-agent RL to the forefront of AI research. While studying for his Ph.D., Jakob interned at Google Brain, OpenAI, and DeepMind. Prior to that, he obtained a first-class honours Bachelor's and Master's degree in Physics from the University of Cambridge, and spent four years with Goldman Sachs and Google. Jakob has also been involved in a number of research projects in systems neuroscience, including work with MIT and research at the Weizmann Institute.

Jakob's Publications

March 14, 2019

RESEARCH

NLP

On the Pitfalls of Measuring Emergent Communication

How do we know if communication is emerging in a multi-agent system? The vast majority of recent papers on emergent communication show that adding a communication channel leads to an increase in reward or task success. This is a useful…

Ryan Lowe, Jakob Foerster, Y-Lan Boureau, Joelle Pineau, Yann Dauphin,

March 14, 2019