Multi-Agent Universe Environment


#1

Is anyone aware of a multi-agent Universe environment?

What I’m interested to do is like point 4. (a complex simulation with many long-lived agents) : https://openai.com/blog/special-projects/

Thank you.


#2

Solved with Roboschool https://blog.openai.com/roboschool/

Roboschool also makes it easy to train multiple agents together in the same environment.