We're open-sourcing a multiagent environment based on the highly popular card game Hanabi, & an agent based on the Dopamine framework! w/ & al. Here's a short post about the project:
Also take a look at co-author Marc G. Bellemare’s blog post on how the Hanabi Learning Environment can move AI forward.
A cooperative benchmark: Announcing the Hanabi Learning Environment , #AI, #MachineLearning