Our Fellows program turns people with software experience into ML practitioners, helping them make real contributions within only a small number of months. The latest example:
Excited to share the work I've done during my @OpenAI Fellowship! Using a new procedurally generated environment called CoinRun, we measure how well trained agents can generalize to new environments: blog.openai.com/quantifying-…

Dec 6, 2018 · 5:15 PM UTC

2
6
58
Replying to @gdb
Is the program available for foreign applicants?
1
Replying to @gdb
Are there any plans for another Requests for Research? I noticed several interesting research directions shared at the end of this paper, including investigating the relationship between environment complexity and the number of levels required for good generalization