AISC3: Research Summaries

The third AI Safety Camp took place in April 2019 in Madrid. Our teams have worked on exciting projects which are summarized below:

Categorizing Wireheading in Partially Embedded Agents:

Team: Embedded agents –  Arushi, Davide, Sayan
We presented our work at the AI Safety Workshop in IJCAI 2019.
Read our paper here.

AI Safety Debate and Its Applications:

Team: Debate – Vojta Kovarik, Anna Gajdova, David Lindner, Lukas Finnveden, Rajashree Agrawal

Read our blog post here. 
See our GitHub here.

Regularization and visualization of attention in reinforcement learning agents

Team: Dmitry Nikulin, Sebastian Kosch, Fabian Steuer, Hoagy Cunningham

Read our research report here.

Leave a Comment

Your email address will not be published. Required fields are marked *